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

    Neuronpedia

    INDEX
    Explanations

    (String

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bron
    -0.07
    镜
    -0.07
     crash
    -0.07
    getState
    -0.06
     Binder
    -0.06
     Keystone
    -0.06
     hackers
    -0.06
    opol
    -0.06
     judge
    -0.06
    achten
    -0.06
    POSITIVE LOGITS
    ButtonTitles
    0.06
    lán
    0.06
     символ
    0.06
    							
↵
    0.06
     USERNAME
    0.06
    .ind
    0.06
     Svět
    0.06
    少女
    0.06
     tricks
    0.06
     Twins
    0.06
    Act Density 0.001%

    No Known Activations