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

    Neuronpedia

    INDEX
    Explanations

    and/or punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +p
    -0.07
    їх
    -0.07
     التي
    -0.07
    cky
    -0.07
    /**
    -0.06
    萨
    -0.06
     Charging
    -0.06
     白
    -0.06
     يوليو
    -0.06
    ";
    -0.06
    POSITIVE LOGITS
    .Metro
    0.07
    relation
    0.07
    stdarg
    0.06
     unknow
    0.06
     currentIndex
    0.06
     UIT
    0.06
    ()">↵
    0.06
    CONF
    0.06
    Attrib
    0.06
     hedef
    0.06
    Act Density 0.071%

    No Known Activations