Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numerical data and types of terms associated with measurements or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Numbers followed by mathematical symbols

    np_acts-logits-general · gemini-2.0-flash

    numbers and days of the week

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -1.02
     pleaſure
    -0.93
     myſelf
    -0.93
     itſelf
    -0.86
     betweenstory
    -0.85
     Monfieur
    -0.84
    +:+
    -0.84
     Chriftian
    -0.83
    ConstraintMaker
    -0.82
     disambiguazione
    -0.81
    POSITIVE LOGITS
     Monday
    0.51
    2
    0.40
    Monday
    0.40
    1
    0.40
     Eins
    0.39
     lundi
    0.38
     val
    0.38
     Tuesday
    0.36
     selv
    0.36
    保
    0.35
    Act Density 0.350%

    No Known Activations