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

    Neuronpedia

    INDEX
    Explanations

    grand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     各
    -0.08
     eliminating
    -0.07
    ert
    -0.07
     disbelief
    -0.07
    vo
    -0.06
    relevant
    -0.06
     Afterwards
    -0.06
     بعضی
    -0.06
    efficient
    -0.06
    ंधन
    -0.06
    POSITIVE LOGITS
     grand
    0.12
    ليزية
    0.07
    (action
    0.06
    _FINE
    0.06
     PropertyChanged
    0.06
     أعلام
    0.06
    $product
    0.06
    _serial
    0.06
     Ре
    0.06
     claim
    0.06
    Act Density 0.002%

    No Known Activations