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

    Neuronpedia

    INDEX
    Explanations

    only successful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    poque
    0.90
    sparsity
    0.89
     frequência
    0.84
     frecuencia
    0.83
     avoidable
    0.83
    caire
    0.82
    servicetime
    0.82
    blurred
    0.79
    consistency
    0.79
    currentTime
    0.79
    POSITIVE LOGITS
     Geology
    0.86
     geology
    0.85
     Geological
    0.85
    trä
    0.83
    Fetch
    0.80
    olg
    0.78
    輸送
    0.74
    anks
    0.74
     geological
    0.74
    anko
    0.73
    Act Density 0.000%

    No Known Activations