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

    Neuronpedia

    INDEX
    Explanations

    pip install

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Paxos
    0.72
    MPa
    0.70
    raquinone
    0.68
    microphone
    0.66
     toroidal
    0.65
     Vinc
    0.65
     triphosphate
    0.65
     Mikro
    0.63
     MPa
    0.62
    tp
    0.62
    POSITIVE LOGITS
    挔
    0.63
     H
    0.63
    H
    0.63
     خر
    0.62
     ハ
    0.61
    sti
    0.61
     வேற
    0.60
     সু
    0.59
    bė
    0.58
     الح
    0.58
    Act Density 0.276%

    No Known Activations