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

    Neuronpedia

    INDEX
    Explanations

    Space

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ragaz
    -0.07
     إن
    -0.07
    modelName
    -0.07
    �
    -0.07
    um
    -0.07
     kend
    -0.07
    <Card
    -0.07
     أن
    -0.06
    uat
    -0.06
    pong
    -0.06
    POSITIVE LOGITS
    _track
    0.07
    쁘
    0.07
     clim
    0.07
    /env
    0.07
    剪
    0.07
    exec
    0.07
     Clarkson
    0.06
    垌
    0.06
     commission
    0.06
    _SELECTION
    0.06
    Act Density 0.001%

    No Known Activations