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

    Neuronpedia

    INDEX
    Explanations

    Alicia

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ос
    -0.07
     regimes
    -0.06
    ะ
    -0.06
     carriers
    -0.06
     düzen
    -0.06
    species
    -0.06
    ’ve
    -0.06
     leben
    -0.06
    unknown
    -0.06
    ็น
    -0.06
    POSITIVE LOGITS
    struction
    0.08
    ica
    0.07
     तह
    0.07
    athi
    0.07
    لال
    0.07
    oldem
    0.07
    _THEME
    0.07
    .To
    0.06
    akash
    0.06
     праці
    0.06
    Act Density 0.003%

    No Known Activations