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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ania
    -0.07
    ret
    -0.07
     slew
    -0.06
    _bin
    -0.06
    Shift
    -0.06
     populate
    -0.06
     cambio
    -0.06
     pretend
    -0.06
     combined
    -0.06
     farm
    -0.06
    POSITIVE LOGITS
    lassian
    0.07
    upil
    0.07
    �
    0.07
     елек
    0.06
     Микола
    0.06
    artifact
    0.06
    .story
    0.06
    uyện
    0.06
    )["
    0.06
    39
    0.06
    Act Density 0.002%

    No Known Activations