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

    Neuronpedia

    INDEX
    Explanations

    without

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    0.64
    RPG
    0.63
    Upgrade
    0.59
    improvement
    0.58
    Related
    0.57
    bridges
    0.57
    urgent
    0.56
    fficacy
    0.56
    riter
    0.55
    forder
    0.55
    POSITIVE LOGITS
     devoid
    1.54
    无
    1.53
     zero
    1.52
     शून्य
    1.52
    無
    1.49
     inaction
    1.48
     无
    1.47
     inactivity
    1.45
     без
    1.44
     empty
    1.39
    Act Density 2.404%

    No Known Activations