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

    Neuronpedia

    INDEX
    Explanations

    technical questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _RET
    -0.07
     Frequency
    -0.06
     Communities
    -0.06
     queued
    -0.06
     вокруг
    -0.06
    -0.06
    _conditions
    -0.05
    ขณะ
    -0.05
    ;x
    -0.05
    aters
    -0.05
    POSITIVE LOGITS
    .et
    0.07
    تیجه
    0.07
    acak
    0.07
    .bucket
    0.07
     입니다
    0.06
     Bul
    0.06
    остей
    0.06
     место
    0.06
    Honestly
    0.06
    ніх
    0.06
    Act Density 0.100%

    No Known Activations