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

    Neuronpedia

    INDEX
    Explanations

    Central Perk, tidal flow, fare reduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    as
    0.63
    en
    0.54
    ig
    0.52
    ec
    0.49
    eq
    0.49
    лен
    0.48
    ást
    0.47
    le
    0.47
    쿠
    0.47
    esia
    0.46
    POSITIVE LOGITS
     IME
    0.50
     style
    0.50
     craz
    0.49
     cikin
    0.49
     snakes
    0.47
     BufferedWriter
    0.47
     lu
    0.46
     query
    0.46
     fondness
    0.46
     QUERY
    0.45
    Act Density 0.000%

    No Known Activations