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

    Neuronpedia

    INDEX
    Explanations

    software configuration/UI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    460
    -0.07
    642
    -0.06
    vl
    -0.06
    585
    -0.06
    604
    -0.06
    :def
    -0.06
    .exist
    -0.06
    .When
    -0.06
     Esp
    -0.06
    mut
    -0.06
    POSITIVE LOGITS
    逐
    0.07
     ($('#
    0.07
    ература
    0.07
    _GOOD
    0.06
    Secretary
    0.06
    })↵↵↵
    0.06
    structors
    0.06
    ');↵↵↵
    0.06
     soğ
    0.06
    賢
    0.06
    Act Density 0.270%

    No Known Activations