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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     encuentra
    -0.07
    -ton
    -0.06
     되었다
    -0.06
     pobl
    -0.06
    fifo
    -0.06
    .usage
    -0.06
    िन
    -0.06
     thaimassage
    -0.06
     azal
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    ków
    0.08
     illustrating
    0.07
    .GetFiles
    0.07
    Khi
    0.07
    Focus
    0.07
    ?)↵↵
    0.06
    nish
    0.06
     đêm
    0.06
    اش
    0.06
     percentile
    0.06
    Act Density 0.021%

    No Known Activations