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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yy
    -0.07
    itempty
    -0.06
    .Multiline
    -0.06
    -in
    -0.06
     mar
    -0.06
     cof
    -0.06
    _HALF
    -0.06
     protr
    -0.06
     Retrie
    -0.06
    isdigit
    -0.06
    POSITIVE LOGITS
     россий
    0.07
    )))))↵
    0.07
    след
    0.07
     cattle
    0.07
    beautiful
    0.07
     ।↵
    0.06
     affection
    0.06
    िछ
    0.06
     explore
    0.06
    ANE
    0.06
    Act Density 0.000%

    No Known Activations