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

    Neuronpedia

    INDEX
    Explanations

    IDs in code/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LECTION
    -0.06
    едж
    -0.06
    ože
    -0.06
    850
    -0.06
    .identity
    -0.06
     appliances
    -0.06
    read
    -0.06
    ervo
    -0.06
    Pets
    -0.06
    иболее
    -0.05
    POSITIVE LOGITS
    .sw
    0.07
    طر
    0.07
     depict
    0.07
    ح
    0.07
     favour
    0.07
    Mother
    0.06
    ูแล
    0.06
    short
    0.06
     thù
    0.06
     Actor
    0.06
    Act Density 0.118%

    No Known Activations