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

    Neuronpedia

    INDEX
    Explanations

    function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۍ
    0.82
    ]}$.
    0.65
     loro
    0.65
     deras
    0.64
    로나
    0.62
    ዋል።
    0.62
    ς
    0.62
    )}^{\
    0.61
     deren
    0.61
    get
    0.60
    POSITIVE LOGITS
    se
    0.86
     bullshit
    0.76
     धमकी
    0.73
     Illness
    0.73
    的内容
    0.72
     qubits
    0.72
     wyja
    0.72
     perjury
    0.72
    gada
    0.72
     fatalities
    0.72
    Act Density 0.549%

    No Known Activations