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

    Neuronpedia

    INDEX
    Explanations

    Okay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᓱ
    0.43
     nodding
    0.39
     терпе
    0.39
     ●
    0.38
     ◎
    0.38
     THANK
    0.38
    cheon
    0.37
    峮
    0.37
     पै
    0.36
    why
    0.36
    POSITIVE LOGITS
    Incrementor
    0.45
     APO
    0.41
     antagonism
    0.40
     पुरे
    0.39
    intersects
    0.38
     randomised
    0.38
    Hipp
    0.38
     proposals
    0.38
     gradients
    0.38
    వల
    0.37
    Act Density 0.000%

    No Known Activations