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

    Neuronpedia

    INDEX
    Explanations

    shadow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    empresa
    -0.07
     rifles
    -0.07
    _EQUALS
    -0.07
    _reaction
    -0.07
    _INSTALL
    -0.06
     tec
    -0.06
     nineteen
    -0.06
    Parents
    -0.06
     チ
    -0.06
     入
    -0.06
    POSITIVE LOGITS
     Shadow
    0.14
     shadow
    0.13
    shadow
    0.12
    Shadow
    0.10
    .shadow
    0.10
    ADOW
    0.09
     Shadows
    0.09
    _shadow
    0.09
     shadows
    0.08
    adow
    0.08
    Act Density 0.003%

    No Known Activations