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

    Neuronpedia

    INDEX
    Explanations

    managing technical entities and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    怨
    0.51
     catégories
    0.50
     enemigos
    0.50
     никак
    0.49
    ErrorReport
    0.47
    äsident
    0.46
    友
    0.46
    ínas
    0.46
    伀
    0.46
    ínez
    0.46
    POSITIVE LOGITS
    н
    0.54
    ن
    0.53
    nft
    0.47
     playthrough
    0.47
    n
    0.46
     can
    0.46
    vet
    0.46
     בשנת
    0.45
     pictures
    0.44
    ン
    0.44
    Act Density 0.000%

    No Known Activations