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

    Neuronpedia

    INDEX
    Explanations

    ending with -ic, -ive, or contain eff

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    الي
    -0.07
    Iterable
    -0.06
    ("'"
    -0.06
    113
    -0.06
    олос
    -0.06
    Below
    -0.06
    Trees
    -0.06
    险
    -0.06
    826
    -0.06
     —↵
    -0.06
    POSITIVE LOGITS
     číslo
    0.07
     parce
    0.07
     pohled
    0.06
     عکس
    0.06
    _STR
    0.06
     textSize
    0.06
     připom
    0.06
    (RE
    0.06
    циклоп
    0.06
     pornôs
    0.06
    Act Density 0.002%

    No Known Activations