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

    Neuronpedia

    INDEX
    Explanations

    ski resort, loop quantum gravity, law

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     endere
    0.97
     cortar
    0.92
     elige
    0.91
     elegido
    0.89
     jogadores
    0.88
     এছাড়াও
    0.88
     integrado
    0.87
     adequado
    0.87
     adquirido
    0.87
    чёт
    0.86
    POSITIVE LOGITS
    š
    0.98
    े
    0.89
    ו
    0.89
    IT
    0.84
    ため
    0.84
    나
    0.83
    er
    0.82
     ITS
    0.82
    ELI
    0.80
    HAEL
    0.80
    Act Density 0.005%

    No Known Activations