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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    128
    -0.07
    Studies
    -0.07
    _locale
    -0.07
     prin
    -0.07
    foo
    -0.06
    िष
    -0.06
    -year
    -0.06
     nobody
    -0.06
    気
    -0.06
    -Д
    -0.06
    POSITIVE LOGITS
     Pass
    0.06
    _music
    0.06
     Tiles
    0.06
     ช
    0.05
     태
    0.05
    .On
    0.05
     jail
    0.05
     specificity
    0.05
     kurs
    0.05
     doğ
    0.05
    Act Density 0.011%

    No Known Activations