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

    Neuronpedia

    INDEX
    Explanations

    inability/disbelief

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     naš
    -0.07
    انس
    -0.07
     things
    -0.07
     ít
    -0.06
    لا
    -0.06
    _rate
    -0.06
    Pixels
    -0.06
    boss
    -0.06
     Canvas
    -0.06
    .res
    -0.06
    POSITIVE LOGITS
    _MA
    0.06
     bald
    0.06
     Ord
    0.06
     progressing
    0.06
     подаль
    0.06
     &:
    0.06
    _COMMIT
    0.06
    uspended
    0.05
    ��
    0.05
     Chester
    0.05
    Act Density 0.035%

    No Known Activations