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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mustafa
    -0.07
    ------------------------------------------------
    -0.07
     план
    -0.06
    Initialize
    -0.06
     obstruction
    -0.06
     preparing
    -0.06
    astic
    -0.06
    Estado
    -0.06
     deserve
    -0.06
     embraces
    -0.06
    POSITIVE LOGITS
     ydk
    0.07
     UIControl
    0.06
     定
    0.06
    риг
    0.06
    _FRAME
    0.06
    сий
    0.06
     dee
    0.06
     TRY
    0.05
     LETTER
    0.05
     Filters
    0.05
    Act Density 0.002%

    No Known Activations