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

    Neuronpedia

    INDEX
    Explanations

    equations with variables and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iler
    0.69
    до
    0.62
    iden
    0.61
    rological
    0.59
    ponenten
    0.57
    amerikan
    0.56
    लों
    0.54
    ologien
    0.53
    addr
    0.53
    olog
    0.53
    POSITIVE LOGITS
    ু
    0.82
    ק
    0.77
     这是
    0.76
     Noting
    0.76
     exudes
    0.75
    ﻒ
    0.75
    ཥ
    0.75
    目的是
    0.74
    rát
    0.73
    و
    0.73
    Act Density 0.115%

    No Known Activations