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

    Neuronpedia

    INDEX
    Explanations

    haired American

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kfollowers
    0.67
    lcnaf
    0.64
    𒀝
    0.64
    Celeron
    0.64
     vudd
    0.63
    άσ
    0.63
     thisobject
    0.62
     stardom
    0.61
    ائیں۔
    0.61
     químicas
    0.61
    POSITIVE LOGITS
    s
    1.20
    '
    0.75
     y
    0.74
     de
    0.69
    ，
    0.68
    sion
    0.67
    di
    0.66
    sir
    0.65
    ،
    0.65
     Resilience
    0.61
    Act Density 0.000%

    No Known Activations