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

    Neuronpedia

    INDEX
    Explanations

    heading toward something negative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     expresses
    -0.06
    学院
    -0.06
     دی
    -0.06
     میتوان
    -0.06
     larvae
    -0.06
     lég
    -0.06
     Bạn
    -0.06
     editors
    -0.06
     stretching
    -0.06
     censor
    -0.06
    POSITIVE LOGITS
    ReactDOM
    0.07
     meas
    0.07
    Conv
    0.07
     =$
    0.07
     WINAPI
    0.06
     pNode
    0.06
    ADATA
    0.06
    тив
    0.06
    EFF
    0.06
     Sept
    0.06
    Act Density 0.065%

    No Known Activations