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
    шир
    -0.07
    荒
    -0.07
    ternet
    -0.06
    grams
    -0.06
    -speaking
    -0.06
    bracht
    -0.06
     adrenal
    -0.06
    div
    -0.06
    tal
    -0.06
     fostering
    -0.06
    POSITIVE LOGITS
    '´
    0.07
     With
    0.07
    .removeChild
    0.06
    　　 　 　
    0.06
    取り
    0.06
    .abort
    0.06
     thủ
    0.06
    払
    0.06
     Rachel
    0.06
     Venice
    0.06
    Act Density 0.000%

    No Known Activations