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

    Neuronpedia

    INDEX
    Explanations

    helping

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gradual
    -0.07
     strict
    -0.07
     gio
    -0.06
     informs
    -0.06
    と思
    -0.06
     rise
    -0.06
     sudo
    -0.06
     chất
    -0.06
     sized
    -0.06
    cosity
    -0.06
    POSITIVE LOGITS
    AMILY
    0.07
    ửa
    0.06
    tuple
    0.06
    μενη
    0.06
     Gia
    0.06
    !!)↵
    0.06
    !!↵
    0.06
    ิน
    0.06
     Alicia
    0.06
    wives
    0.06
    Act Density 0.076%

    No Known Activations