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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (prefix
    -0.07
     jpg
    -0.07
    ’re
    -0.06
    COM
    -0.06
    XS
    -0.06
    Txt
    -0.06
    uyor
    -0.06
    Alert
    -0.06
    .keys
    -0.06
    Wow
    -0.06
    POSITIVE LOGITS
     Deadline
    0.07
     наказ
    0.07
     haystack
    0.06
    Deadline
    0.06
    iked
    0.06
     Rav
    0.06
     Bodies
    0.06
    _MODE
    0.06
    قول
    0.06
     elektron
    0.06
    Act Density 0.176%

    No Known Activations