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

    Neuronpedia

    INDEX
    Explanations

    actions and origins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    За
    0.61
    Следу
    0.58
    З
    0.57
     Ком
    0.54
    Ком
    0.54
    :"+
    0.53
    Motors
    0.53
    К
    0.53
    ோர
    0.52
     immunoblot
    0.52
    POSITIVE LOGITS
    ↵
    0.54
    ﻲ
    0.54
     painful
    0.51
     does
    0.49
    คู่
    0.48
    ?
    0.46
     собственного
    0.45
     much
    0.45
    loin
    0.45
     מה
    0.45
    Act Density 0.000%

    No Known Activations