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

    Neuronpedia

    INDEX
    Explanations

    core components or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.61
    ע
    0.59
    v
    0.55
    j
    0.53
    ارك
    0.50
     а
    0.48
    ต์
    0.47
    ება
    0.47
    '
    0.45
    າ
    0.44
    POSITIVE LOGITS
     and
    0.57
     at
    0.56
    ene
    0.49
     for
    0.47
    ado
    0.44
    ad
    0.42
    ak
    0.42
    적인
    0.41
     session
    0.41
     svært
    0.39
    Act Density 0.589%

    No Known Activations