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

    Neuronpedia

    INDEX
    Explanations

    classes and inheritance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (selector
    -0.06
    irected
    -0.06
     právě
    -0.06
    (repo
    -0.06
    _fsm
    -0.06
     İşte
    -0.06
    ynı
    -0.06
     ngoài
    -0.06
     corners
    -0.06
     Drum
    -0.05
    POSITIVE LOGITS
    tright
    0.07
     quantitative
    0.06
     ripping
    0.06
     Originally
    0.06
     subpoena
    0.06
    ption
    0.06
    rstrip
    0.06
     hiệu
    0.06
     Query
    0.06
     �
    0.06
    Act Density 0.008%

    No Known Activations