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

    Neuronpedia

    INDEX
    Explanations

    access control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тацию
    0.46
    aprend
    0.44
     احتيا
    0.43
     hoạt
    0.43
    unsubscribe
    0.42
    antwoord
    0.42
    }"),
    0.41
    说是
    0.41
    ርዓ
    0.41
    vita
    0.41
    POSITIVE LOGITS
     Access
    0.77
     ACCESS
    0.73
    ibly
    0.70
    Access
    0.68
     access
    0.66
     acess
    0.64
    oire
    0.59
    ACCESS
    0.58
    ORIES
    0.57
     acceder
    0.56
    Act Density 0.028%

    No Known Activations