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

    Neuronpedia

    INDEX
    Explanations

    HTML code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ful
    -0.07
    nos
    -0.07
     �
    -0.07
    _app
    -0.07
    _within
    -0.07
     هر
    -0.06
     bean
    -0.06
    _filtered
    -0.06
    param
    -0.06
     asynchronous
    -0.06
    POSITIVE LOGITS
     perks
    0.07
    フ�
    0.06
     tekst
    0.06
     trailing
    0.06
     ＜
    0.06
    SectionsIn
    0.06
     spikes
    0.06
     şark
    0.05
     Chiến
    0.05
    ΟΔ
    0.05
    Act Density 0.032%

    No Known Activations