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

    Neuronpedia

    INDEX
    Explanations

    see

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (has
    -0.06
    525
    -0.06
    _ray
    -0.06
    Swap
    -0.06
    芙
    -0.06
    Yo
    -0.06
     تولید
    -0.06
    read
    -0.06
     raging
    -0.06
     Kings
    -0.06
    POSITIVE LOGITS
    .setResult
    0.07
    rather
    0.07
    �
    0.07
     moistur
    0.06
     &
    0.06
    :-------------</
    0.06
    ọc
    0.06
     originates
    0.06
    áli
    0.06
    (response
    0.06
    Act Density 0.014%

    No Known Activations