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

    Neuronpedia

    INDEX
    Explanations

    immense

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    configurable
    0.47
    华
    0.46
    華
    0.42
    دي
    0.42
    ëren
    0.42
    offers
    0.41
     descansar
    0.41
    闪
    0.41
    дый
    0.40
    éto
    0.39
    POSITIVE LOGITS
     privile
    0.51
    ো
    0.49
     privilegio
    0.48
    丶
    0.46
     chast
    0.46
     savag
    0.45
    pam
    0.45
     ordine
    0.44
     relazione
    0.44
     italics
    0.44
    Act Density 0.000%

    No Known Activations