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

    Neuronpedia

    INDEX
    Explanations

    Theme

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _AGENT
    -0.09
     Hos
    -0.08
    _files
    -0.07
    "As
    -0.07
    btc
    -0.07
    يات
    -0.07
    /sw
    -0.06
    JE
    -0.06
    Bien
    -0.06
    _middle
    -0.06
    POSITIVE LOGITS
     ihtiyaç
    0.08
    fol
    0.07
     美国
    0.06
    ovement
    0.06
     خدمات
    0.06
     logfile
    0.06
     femmes
    0.06
     autoload
    0.06
    !“↵↵
    0.06
    ################################################################
    0.06
    Act Density 0.000%

    No Known Activations