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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     writing
    -0.07
     drill
    -0.07
    רצה
    -0.07
     đêm
    -0.07
     recover
    -0.07
    чество
    -0.06
     >::
    -0.06
    ceiving
    -0.06
     reflects
    -0.06
     Header
    -0.06
    POSITIVE LOGITS
    ¾
    0.07
    _closure
    0.07
    崇拜
    0.07
    也不知道
    0.07
    mö
    0.07
    _DUMP
    0.07
     mafia
    0.07
     offers
    0.07
    確か
    0.07
    .SQLite
    0.06
    Act Density 0.106%

    No Known Activations