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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ']*
    -0.07
     Chain
    -0.07
    /crypto
    -0.06
     RestClient
    -0.06
     submitting
    -0.06
    できる
    -0.06
     communities
    -0.06
     IMO
    -0.06
     Darling
    -0.06
     strtolower
    -0.06
    POSITIVE LOGITS
    öl
    0.07
    독
    0.07
    scribers
    0.07
    always
    0.07
    atives
    0.06
    tracker
    0.06
    jud
    0.06
    assel
    0.06
     Заг
    0.06
     όλα
    0.06
    Act Density 0.022%

    No Known Activations