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

    Neuronpedia

    INDEX
    Explanations

    and or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RCT
    -0.07
    ERG
    -0.07
     سلام
    -0.07
     carrera
    -0.06
     KH
    -0.06
     сал
    -0.06
     Piet
    -0.06
     HIT
    -0.06
     PU
    -0.06
     dire
    -0.06
    POSITIVE LOGITS
    ắc
    0.07
    аци
    0.07
    ,d
    0.07
    ,D
    0.06
    Extension
    0.06
    烟
    0.06
    .engine
    0.06
    jac
    0.06
    nesota
    0.06
    σο
    0.06
    Act Density 0.068%

    No Known Activations