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

    Neuronpedia

    INDEX
    Explanations

    Rapid processes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thoroughly
    -0.07
    ":{"
    -0.07
    rics
    -0.07
    Page
    -0.07
    ěř
    -0.07
    kel
    -0.06
    set
    -0.06
    _import
    -0.06
    forget
    -0.06
     bots
    -0.06
    POSITIVE LOGITS
     elimination
    0.07
    VRTX
    0.07
     کم
    0.06
     응
    0.06
     phản
    0.06
    retain
    0.06
     citiz
    0.06
     köy
    0.06
    _CC
    0.06
    ีน
    0.06
    Act Density 0.005%

    No Known Activations