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

    Neuronpedia

    INDEX
    Explanations

    Describing processes and actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     укра
    -0.06
     kir
    -0.06
     тела
    -0.06
     Lana
    -0.06
     الاخ
    -0.06
    來
    -0.06
     وظ
    -0.06
    γο
    -0.06
    tones
    -0.06
    女
    -0.06
    POSITIVE LOGITS
     duly
    0.07
    .ADD
    0.06
    rix
    0.06
     relentless
    0.06
    (circle
    0.06
     LINUX
    0.06
    Toronto
    0.06
     arr
    0.06
    _GE
    0.06
    _duration
    0.06
    Act Density 0.001%

    No Known Activations