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

    Neuronpedia

    INDEX
    Explanations

    sex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     },
↵
↵
    -0.07
    boy
    -0.07
     collections
    -0.07
    alling
    -0.07
    Appending
    -0.07
    (){
↵
↵
    -0.06
    mites
    -0.06
    岳
    -0.06
    דר
    -0.06
    Dict
    -0.06
    POSITIVE LOGITS
    _errno
    0.07
    -functional
    0.07
     AMP
    0.07
    ══
    0.07
    (comm
    0.07
    patible
    0.06
    -beta
    0.06
    _cycles
    0.06
    laşma
    0.06
    ㎰
    0.06
    Act Density 0.154%

    No Known Activations