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

    Neuronpedia

    INDEX
    Explanations

    say comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     abortions
    -0.08
    容纳
    -0.07
    这对于
    -0.07
    TAIL
    -0.07
     información
    -0.06
     notifying
    -0.06
    رهاب
    -0.06
     Bugs
    -0.06
    rel
    -0.06
     mandatory
    -0.06
    POSITIVE LOGITS
    uku
    0.07
     Unc
    0.07
    ulti
    0.07
    Due
    0.07
    爱
    0.07
     situação
    0.06
    世
    0.06
     Edward
    0.06
    $ar
    0.06
    -neutral
    0.06
    Act Density 0.004%

    No Known Activations