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

    Neuronpedia

    INDEX
    Explanations

    estimating and guessing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sublim
    0.41
     paradigm
    0.41
     intracellular
    0.40
     radiative
    0.40
     jeżeli
    0.39
     ausreiche
    0.36
    ずっと
    0.36
     由于
    0.36
     dichlor
    0.35
     BRIEF
    0.35
    POSITIVE LOGITS
     guesses
    0.55
     either
    0.54
     estimados
    0.54
    只好
    0.53
    Estimate
    0.52
     guesswork
    0.52
     estima
    0.50
     entweder
    0.49
     estimations
    0.48
    Estim
    0.48
    Act Density 0.000%

    No Known Activations