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

    Neuronpedia

    INDEX
    Explanations

    Initialisms and IPOs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     originally
    0.47
     earliest
    0.43
     originals
    0.42
     রাখা
    0.42
    originally
    0.42
     zunächst
    0.42
    ように
    0.41
     indeed
    0.39
     сначала
    0.39
     mainly
    0.38
    POSITIVE LOGITS
    ization
    0.73
    isation
    0.71
    izing
    0.67
    izarea
    0.62
    ização
    0.60
    ising
    0.59
    izations
    0.59
    izers
    0.58
    izr
    0.55
    화를
    0.54
    Act Density 0.016%

    No Known Activations