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

    Neuronpedia

    INDEX
    Explanations

    place name or origin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hostels
    0.82
     hamming
    0.79
    candle
    0.78
     chibi
    0.76
    <%@
    0.75
     paesi
    0.75
    !=
    0.74
    0.74
     trigonometric
    0.74
     desconto
    0.74
    POSITIVE LOGITS
     vor
    0.75
    ili
    0.68
    ufs
    0.64
    ener
    0.61
     sort
    0.59
     fur
    0.58
    追
    0.58
     titel
    0.58
     zunächst
    0.57
     nærm
    0.57
    Act Density 0.000%

    No Known Activations