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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     INIT
    -0.06
    tim
    -0.06
     Processor
    -0.06
    �t
    -0.06
    .street
    -0.06
     trick
    -0.06
    �택
    -0.06
     Raises
    -0.06
    :id
    -0.06
    .getD
    -0.06
    POSITIVE LOGITS
     />
    0.07
     ancora
    0.07
    ΟΣ
    0.06
    概
    0.06
    至
    0.06
     dying
    0.06
     ευ
    0.06
    较
    0.06
    طبي
    0.06
    간
    0.06
    Act Density 0.000%

    No Known Activations