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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rubio
    -0.07
    哭
    -0.07
    گل
    -0.06
     defenses
    -0.06
    齐
    -0.06
     counties
    -0.06
     ハ
    -0.06
    oggled
    -0.06
     adultery
    -0.06
     SAM
    -0.06
    POSITIVE LOGITS
     datatype
    0.07
    .air
    0.07
    (dw
    0.06
     elementType
    0.06
    春
    0.06
     hver
    0.06
     Bow
    0.06
    <Color
    0.06
    .MapPath
    0.06
    GCC
    0.06
    Act Density 0.031%

    No Known Activations