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

    Neuronpedia

    INDEX
    Explanations

    math/physics symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    59
    -0.07
    219
    -0.07
     veren
    -0.06
    859
    -0.06
     backlash
    -0.06
     hel
    -0.06
     qp
    -0.06
     pH
    -0.06
     nominal
    -0.06
    501
    -0.06
    POSITIVE LOGITS
    íš
    0.07
    BYTE
    0.06
    ARRY
    0.06
     doctors
    0.06
    atile
    0.06
    っく
    0.06
    ắ
    0.06
    arDown
    0.06
     STORE
    0.06
    _fetch
    0.06
    Act Density 0.030%

    No Known Activations