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

    Neuronpedia

    INDEX
    Explanations

    profit or loss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ŕ
    0.89
    Sexual
    0.88
    Ach
    0.84
    ።
    0.84
     పాటు
    0.83
    ადა
    0.83
    Incorpor
    0.83
    クタ
    0.82
    పాటు
    0.82
    Retour
    0.81
    POSITIVE LOGITS
    6
    0.80
     mindre
    0.78
     adecuadas
    0.77
     adecuados
    0.77
    nal
    0.76
     los
    0.75
    ivasena
    0.74
    nab
    0.73
     agricoles
    0.73
     adecuada
    0.72
    Act Density 0.000%

    No Known Activations