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

    Neuronpedia

    INDEX
    Explanations

    pieces bought or reduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    imetable
    0.51
    p
    0.50
    fot
    0.49
    PHOT
    0.49
    USSR
    0.48
    il
    0.48
    ip
    0.47
    ib
    0.47
    peau
    0.47
    azion
    0.46
    POSITIVE LOGITS
     boric
    0.50
     Expand
    0.46
     processor
    0.46
     started
    0.45
    第一时间
    0.44
     apuesta
    0.43
    扩展
    0.43
     resolver
    0.43
    芠
    0.42
     Annie
    0.42
    Act Density 0.004%

    No Known Activations