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

    Neuronpedia

    INDEX
    Explanations

    joyful

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hombres
    -0.07
    (Node
    -0.07
     cerco
    -0.06
    pegawai
    -0.06
     zákaz
    -0.06
     CallingConvention
    -0.06
     dün
    -0.06
     заболева
    -0.06
     sınav
    -0.06
    <a
    -0.06
    POSITIVE LOGITS
    _reports
    0.08
    reports
    0.07
     thrilled
    0.07
    党
    0.07
     Touch
    0.07
    unes
    0.07
    lust
    0.06
    UNE
    0.06
    365
    0.06
    ยม
    0.06
    Act Density 0.047%

    No Known Activations