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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MeasureSpec
    -0.07
    над
    -0.07
    ють
    -0.07
     úřad
    -0.07
    heiten
    -0.06
    меч
    -0.06
     kaufen
    -0.06
     Snake
    -0.06
    문
    -0.06
     نوشته
    -0.06
    POSITIVE LOGITS
    (pm
    0.07
     �
    0.07
    ="{
    0.07
     tossed
    0.06
    .Remote
    0.06
    ảm
    0.06
    _nth
    0.06
    [var
    0.06
     akşam
    0.06
    onda
    0.06
    Act Density 0.000%

    No Known Activations