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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     functioning
    0.43
     சுக
    0.40
     stepwise
    0.39
    functioning
    0.39
     bood
    0.38
     stabilité
    0.37
     tussen
    0.37
     trasmissione
    0.36
     werd
    0.36
     dvije
    0.36
    POSITIVE LOGITS
    ో
    0.44
    Tr
    0.43
    Nú
    0.41
    arden
    0.41
     cacao
    0.41
    ers
    0.40
    ною
    0.40
    ávají
    0.40
    ник
    0.39
     马
    0.39
    Act Density 0.001%

    No Known Activations