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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mệ
    -0.06
     OMIT
    -0.06
    -doc
    -0.06
    쓰
    -0.06
    nivel
    -0.06
    nome
    -0.06
    ovo
    -0.06
    Но
    -0.06
    ρή
    -0.06
    новаж
    -0.06
    POSITIVE LOGITS
     James
    0.08
    Native
    0.07
     sayısı
    0.07
    CLS
    0.07
     emergencies
    0.07
    _SID
    0.07
    ean
    0.07
     ls
    0.06
     yes
    0.06
    alia
    0.06
    Act Density 0.000%

    No Known Activations