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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    strcasecmp
    -0.08
    ר
    -0.07
    대행
    -0.06
     integrates
    -0.06
     equivalent
    -0.06
    〈
    -0.06
    well
    -0.06
    ();//
    -0.06
     "");↵
    -0.06
     estimating
    -0.06
    POSITIVE LOGITS
     disciplinary
    0.08
    /callback
    0.06
     Behaviour
    0.06
    ाइट
    0.06
     dém
    0.06
    (Db
    0.06
     DateTimeKind
    0.06
    .OrderByDescending
    0.06
    iliki
    0.06
     vur
    0.06
    Act Density 0.114%

    No Known Activations