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

    Neuronpedia

    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <!--
    -0.08
    好き
    -0.08
     شهد
    -0.08
    强调
    -0.07
    LIK
    -0.07
     freuen
    -0.07
    重点
    -0.07
    <|endoftext|>
    -0.07
     بنت
    -0.07
    사
    -0.07
    POSITIVE LOGITS
     exhausted
    0.12
     невозмож
    0.11
     beschikbare
    0.11
     exhaustion
    0.11
     Exhaust
    0.11
     unable
    0.10
     Unable
    0.10
    无法
    0.10
     inability
    0.10
     imminent
    0.10
    Act Density 0.011%

    No Known Activations