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

    Neuronpedia

    INDEX
    Explanations

    references to measurement or evaluation metrics

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

    Punctuation, especially colons

    np_acts-logits-general · gemini-2.0-flash

    consequence or explanation follows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stdc
    -0.57
     الحره
    -0.56
    ValueStyle
    -0.55
     ModelExpression
    -0.55
    THISDAY
    -0.52
    horabuena
    -0.52
    lève
    -0.52
     Efq
    -0.51
     Mbappe
    -0.50
     المعيارى
    -0.50
    POSITIVE LOGITS
    there
    0.71
     there
    0.71
    namely
    0.65
     дописавши
    0.63
     namely
    0.60
    那就是
    0.59
    )](
    0.58
     the
    0.57
    '),
    0.56
    それは
    0.55
    Act Density 0.211%

    No Known Activations