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

    Neuronpedia

    INDEX
    Explanations

    Difference, offset

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     produktów
    -0.08
     పాల్గ
    -0.08
     camada
    -0.07
    ผลิต
    -0.07
    initiative
    -0.07
     produtos
    -0.07
    托
    -0.07
     invité
    -0.07
     reage
    -0.07
    ssss
    -0.07
    POSITIVE LOGITS
     determined
    0.10
     learned
    0.09
    orrection
    0.09
     correcting
    0.09
     discrepancies
    0.08
     correction
    0.08
    Correction
    0.08
     Correction
    0.08
     humeur
    0.08
     differences
    0.08
    Act Density 0.007%

    No Known Activations