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

    Neuronpedia

    INDEX
    Explanations

    referee, storyteller, world-builder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Heat
    0.67
    The
    0.66
    Significant
    0.62
    Quantum
    0.61
    oluene
    0.58
    Result
    0.58
    Here
    0.58
    例如
    0.57
     The
    0.57
    Report
    0.57
    POSITIVE LOGITS
     navegador
    0.75
     administrar
    0.74
     lako
    0.74
     adventurer
    0.71
     ordenador
    0.71
    たちの
    0.69
     máquina
    0.68
     каттоо
    0.68
     admirers
    0.66
     lucu
    0.66
    Act Density 0.001%

    No Known Activations