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

    Neuronpedia

    INDEX
    Explanations

    changing names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    開発
    -0.07
     keinen
    -0.07
     Penny
    -0.07
     Controlled
    -0.06
    -Israel
    -0.06
     Leslie
    -0.06
     Rotation
    -0.06
    YOU
    -0.06
     выб
    -0.06
     roman
    -0.06
    POSITIVE LOGITS
     Wayback
    0.06
     isot
    0.06
     شناخته
    0.06
    飾
    0.06
     coax
    0.06
    .getProperties
    0.06
    AuthGuard
    0.05
    اورپوینت
    0.05
    .success
    0.05
     Honour
    0.05
    Act Density 0.125%

    No Known Activations