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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    次
    -0.06
    _kses
    -0.06
    _Email
    -0.06
     weighted
    -0.06
    _overlap
    -0.06
    urnished
    -0.06
     magnificent
    -0.06
    .ErrorCode
    -0.06
     наслід
    -0.06
     ambassadors
    -0.06
    POSITIVE LOGITS
     FOR
    0.07
    htub
    0.07
     های
    0.07
    For
    0.07
     Guantanamo
    0.07
     Этот
    0.07
     nonlinear
    0.07
     эти
    0.06
     τρο
    0.06
     forgiveness
    0.06
    Act Density 0.040%

    No Known Activations