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

    Neuronpedia

    INDEX
    Explanations

    CSS code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     могут
    -0.08
     knees
    -0.07
    зем
    -0.06
     geo
    -0.06
    theless
    -0.06
    bole
    -0.06
     nose
    -0.06
    …”
    -0.06
     Ib
    -0.06
     Cowboys
    -0.06
    POSITIVE LOGITS
    _AP
    0.07
    ğını
    0.06
    .cols
    0.06
     notas
    0.06
     Until
    0.06
    (!$
    0.06
    ΑΛ
    0.06
    Jwt
    0.06
    ̂
    0.06
     목소
    0.06
    Act Density 0.003%

    No Known Activations