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

    Neuronpedia

    INDEX
    Explanations

    Section

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     díky
    -0.07
    김
    -0.07
     Item
    -0.07
     casually
    -0.06
    _ID
    -0.06
    Entity
    -0.06
    REM
    -0.06
    visualization
    -0.06
    	HashMap
    -0.06
    <N
    -0.06
    POSITIVE LOGITS
    @↵
    0.07
    Uvs
    0.07
     преж
    0.07
     Ezra
    0.06
    _crossentropy
    0.06
    混合
    0.06
     countryCode
    0.06
     شده
    0.06
     Texans
    0.06
     Judith
    0.06
    Act Density 0.004%

    No Known Activations