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

    Neuronpedia

    INDEX
    Explanations

    acc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _mag
    -0.08
    _ctx
    -0.07
     ↔
    -0.07
     �
    -0.07
     нату
    -0.07
     利
    -0.06
     Christie
    -0.06
     jä
    -0.06
     उ
    -0.06
     листь
    -0.06
    POSITIVE LOGITS
     aç
    0.18
    'acc
    0.18
    ’acc
    0.12
     Aç
    0.10
     occult
    0.09
     ozone
    0.06
     Welt
    0.06
    below
    0.06
     acl
    0.06
     fourth
    0.06
    Act Density 0.002%

    No Known Activations