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

    Neuronpedia

    INDEX
    Explanations

    unique identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    гото
    0.41
     ju
    0.41
    gore
    0.40
     orientado
    0.37
    mont
    0.37
     قومی
    0.36
    progressive
    0.36
     યોજના
    0.36
    Fin
    0.36
    spinal
    0.36
    POSITIVE LOGITS
     ['(?
    0.42
     GALL
    0.39
     Edmund
    0.38
    扁
    0.38
     SIA
    0.37
    तां
    0.37
     Lik
    0.37
    ^{[
    0.36
    厓
    0.35
     LAC
    0.35
    Act Density 0.001%

    No Known Activations