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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iras
    -0.07
    akit
    -0.06
    callbacks
    -0.06
     Hàng
    -0.06
    �
    -0.06
    aliases
    -0.06
     Bolton
    -0.06
    omers
    -0.06
    Sugar
    -0.06
    니아
    -0.06
    POSITIVE LOGITS
     ním
    0.06
     file
    0.06
    _pid
    0.06
    _vert
    0.06
     prone
    0.06
     Image
    0.06
     coursework
    0.06
    _RESOURCE
    0.06
    ’ят
    0.05
    Dates
    0.05
    Act Density 0.044%

    No Known Activations