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

    Neuronpedia

    INDEX
    Explanations

    aid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     astronaut
    -0.06
    _attachments
    -0.06
    мещ
    -0.06
    خت
    -0.06
    さい
    -0.06
    plode
    -0.06
    ments
    -0.06
     Alphabet
    -0.06
     Split
    -0.06
    apis
    -0.06
    POSITIVE LOGITS
     vind
    0.07
    ротив
    0.06
    $username
    0.06
     litt
    0.06
    สะ
    0.06
     �
    0.06
    [])↵
    0.06
    .scrollTop
    0.06
     Ley
    0.06
     را
    0.06
    Act Density 0.001%

    No Known Activations