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

    Neuronpedia

    INDEX
    Explanations

    structure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OGND
    -0.73
    PointerException
    -0.69
     Efq
    -0.65
     ſtate
    -0.61
     ſeveral
    -0.59
     raiſ
    -0.58
    AccessorTable
    -0.57
    endphp
    -0.57
     contemporaries
    -0.57
     poffible
    -0.57
    POSITIVE LOGITS
     Non
    0.47
    Non
    0.47
    Dee
    0.44
    sion
    0.44
    Ultra
    0.42
    FFF
    0.42
     score
    0.42
    iint
    0.42
    Ass
    0.42
     Credit
    0.42
    Act Density 0.083%

    No Known Activations