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

    Neuronpedia

    INDEX
    Explanations

    Java classes and programming-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +:+
    -0.81
     فريبيس
    -0.76
    ReusableCell
    -0.71
     للاسماء
    -0.69
     كومونز
    -0.68
    __(/*!
    -0.63
    ]")]
    -0.63
    abestanden
    -0.61
    yarnpkg
    -0.60
    ፩
    -0.60
    POSITIVE LOGITS
    IntoConstraints
    0.57
     auroit
    0.36
    paravant
    0.36
     المعيارى
    0.33
     feroit
    0.33
     censiti
    0.32
     malheur
    0.31
     unterkunft
    0.29
    czer
    0.29
     règne
    0.28
    Act Density 0.002%

    No Known Activations