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

    Neuronpedia

    INDEX
    Explanations

    adjunct

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     phổ
    -0.06
    strpos
    -0.06
     royalty
    -0.06
     Penn
    -0.06
     civilizations
    -0.06
    ivity
    -0.06
     puede
    -0.05
    、お
    -0.05
     Poetry
    -0.05
    atoire
    -0.05
    POSITIVE LOGITS
    حية
    0.08
     job
    0.07
    领
    0.07
    QtCore
    0.07
     olursa
    0.07
    ีม
    0.07
     Plus
    0.07
     DISTINCT
    0.07
    тора
    0.07
    DJ
    0.07
    Act Density 0.006%

    No Known Activations