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

    Neuronpedia

    INDEX
    Explanations

    arrives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HP
    -0.07
    	dp
    -0.06
     해
    -0.06
    ーパ
    -0.06
    stem
    -0.06
    ！”↵↵
    -0.06
    лении
    -0.06
    lasting
    -0.06
     translating
    -0.06
    truth
    -0.06
    POSITIVE LOGITS
    _RESULTS
    0.08
    _COL
    0.07
    Digits
    0.06
     吉
    0.06
    _spawn
    0.06
    خص
    0.06
    _phrase
    0.06
    ্�
    0.06
     발매
    0.06
    .sample
    0.06
    Act Density 0.353%

    No Known Activations