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

    Neuronpedia

    INDEX
    Explanations

    code, security, and technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     通販
    -0.79
    ----</
    -0.71
    شهاد
    -0.67
    évaluateur
    -0.65
     Confidence
    -0.65
    LookAnd
    -0.64
    +:+
    -0.64
    تفصیلات
    -0.63
    ViewFeatures
    -0.59
    ATEGY
    -0.58
    POSITIVE LOGITS
     can
    0.60
     depend
    0.54
    GeneratedCode
    0.53
     REL
    0.52
    can
    0.50
    intellij
    0.49
     depended
    0.49
     可
    0.48
    可
    0.48
     lenker
    0.48
    Act Density 0.001%

    No Known Activations