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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     broadcasting
    -0.07
     tema
    -0.07
    .translate
    -0.07
    .realm
    -0.07
     tic
    -0.07
    dados
    -0.06
    র
    -0.06
     yeri
    -0.06
     мн
    -0.06
     привести
    -0.06
    POSITIVE LOGITS
     Large
    0.06
     Sergei
    0.06
    섭
    0.06
    انا
    0.06
    NotEmpty
    0.06
    OVÁ
    0.06
    pecially
    0.06
    .present
    0.06
    Equip
    0.06
     अप
    0.05
    Act Density 0.012%

    No Known Activations