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

    Neuronpedia

    INDEX
    Explanations

    somehow, sometime, some

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suivant
    0.45
     surgi
    0.43
     wholesalers
    0.41
     baixo
    0.40
     χρόνο
    0.40
     achat
    0.39
     inizio
    0.39
     vasena
    0.39
     intervenir
    0.39
     obbl
    0.39
    POSITIVE LOGITS
    !
    0.41
    Instead
    0.38
    PE
    0.38
    Foundation
    0.37
    PR
    0.34
    !"
    0.34
    ender
    0.34
    !'
    0.33
    J
    0.33
    Nik
    0.33
    Act Density 0.000%

    No Known Activations