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

    Neuronpedia

    INDEX
    Explanations

    Technical contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kid
    -0.06
     currentValue
    -0.06
    ))).
    -0.06
    ственная
    -0.06
    likelihood
    -0.06
    �
    -0.06
     تقس
    -0.06
    ита
    -0.06
    ibbean
    -0.06
    ックス
    -0.06
    POSITIVE LOGITS
    .Err
    0.07
     oak
    0.06
     eng
    0.06
     professionally
    0.06
    WithMany
    0.06
    Instagram
    0.06
    ेग
    0.06
    слід
    0.06
     teardown
    0.06
     Sharp
    0.06
    Act Density 0.000%

    No Known Activations