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

    Neuronpedia

    INDEX
    Explanations

    wikipedia categories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igit
    -0.07
    ihan
    -0.07
    endsWith
    -0.06
     поверх
    -0.06
    ạng
    -0.06
     тверд
    -0.06
    арамет
    -0.06
     pé
    -0.06
    ์น
    -0.06
    यह
    -0.06
    POSITIVE LOGITS
     advises
    0.07
     felt
    0.06
     CCD
    0.06
     usando
    0.06
     refused
    0.06
     Guidelines
    0.06
    pu
    0.06
     POSS
    0.06
     जबक
    0.06
    IOR
    0.06
    Act Density 0.010%

    No Known Activations