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

    Neuronpedia

    INDEX
    Explanations

    use to create

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Uwe
    0.45
    abatic
    0.40
    сный
    0.39
    стный
    0.39
     Ć
    0.38
     truc
    0.37
    令
    0.37
     сим
    0.37
     lactic
    0.37
    styl
    0.37
    POSITIVE LOGITS
    idxs
    0.45
     indexed
    0.41
     OCE
    0.41
     sustaining
    0.39
     numerose
    0.39
     remboursement
    0.38
     provisions
    0.38
     alumn
    0.38
     sustain
    0.38
     Desarrollo
    0.38
    Act Density 0.000%

    No Known Activations