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

    Neuronpedia

    INDEX
    Explanations

    releasing and delivering

    np_acts-logits-general · gemini-2.5-flash-lite

    present the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AD
    0.96
     \
    0.85
    ९
    0.84
    ICK
    0.83
    го
    0.82
     ,
    0.77
    다라고
    0.74
     :
    0.73
    larını
    0.72
    larının
    0.72
    POSITIVE LOGITS
    in
    1.32
    s
    1.09
    v
    1.01
    T
    1.01
    u
    0.92
    ווי
    0.84
    et
    0.84
    ש
    0.84
    o
    0.83
    r
    0.82
    Act Density 1.654%

    No Known Activations