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

    Neuronpedia

    INDEX
    Explanations

    Computer hardware product reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     serotonin
    -0.07
    uras
    -0.07
     surve
    -0.07
    UIBarButtonItem
    -0.07
    /do
    -0.07
     إد
    -0.07
     文件
    -0.06
     altered
    -0.06
    anguages
    -0.06
     reliably
    -0.06
    POSITIVE LOGITS
    .EX
    0.07
    MET
    0.07
     ')↵
    0.06
    EEE
    0.06
    hopefully
    0.06
     vbCrLf
    0.06
     rang
    0.06
    GRE
    0.06
    ッグ
    0.06
    >E
    0.06
    Act Density 0.029%

    No Known Activations