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

    Neuronpedia

    INDEX
    Explanations

    -function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    χω
    -0.07
     Classification
    -0.07
     Dustin
    -0.07
    TRIES
    -0.07
     التن
    -0.06
    ㆍ
    -0.06
     GCC
    -0.06
     Array
    -0.06
    osc
    -0.06
    optimize
    -0.06
    POSITIVE LOGITS
     sürekli
    0.08
     residence
    0.06
     initialState
    0.06
    CEED
    0.06
    .mac
    0.06
    _APP
    0.06
     personalities
    0.06
    43
    0.06
     sorts
    0.06
    rl
    0.06
    Act Density 0.009%

    No Known Activations