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

    Neuronpedia

    INDEX
    Explanations

    expressions related to measurable values and comparisons

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

    is followed by numbers or comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.68
     informée
    -0.60
    Personendaten
    -0.53
     RIPRODUZIONE
    -0.51
    pecabe
    -0.50
    GEBURTSDATUM
    -0.49
     uLocal
    -0.49
     Italijani
    -0.48
    Jeografia
    -0.48
     indígen
    -0.47
    POSITIVE LOGITS
     /\.
    0.41
     Beer
    0.41
     the
    0.40
     Pan
    0.39
     again
    0.39
     absentee
    0.38
     Archie
    0.38
    aibo
    0.38
     Soft
    0.38
     Arch
    0.37
    Act Density 0.036%

    No Known Activations