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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     حتی
    -0.08
    ניות
    -0.08
     tabletop
    -0.08
    雨
    -0.08
     vô
    -0.08
     vůbec
    -0.08
     même
    -0.08
     prochaines
    -0.07
     commandes
    -0.07
    เหนือ
    -0.07
    POSITIVE LOGITS
     Replacement
    0.12
     Replace
    0.12
     replaced
    0.12
    Replace
    0.12
     replacement
    0.11
     replace
    0.11
     outdated
    0.11
     remplac
    0.11
     replac
    0.11
    Replacement
    0.11
    Act Density 0.005%

    No Known Activations