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

    Neuronpedia

    INDEX
    Explanations

    cit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ла
    -0.07
    Simulation
    -0.07
     DAG
    -0.06
     handshake
    -0.06
    ustos
    -0.06
    .writer
    -0.06
    oslav
    -0.06
     وسط
    -0.06
     remembered
    -0.06
     참고
    -0.06
    POSITIVE LOGITS
    212
    0.06
    (chr
    0.06
    sit
    0.06
    cit
    0.06
    icit
    0.06
    uming
    0.06
    azi
    0.06
     doi
    0.06
    Scalars
    0.06
    (of
    0.06
    Act Density 0.000%

    No Known Activations