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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     पड़
    -0.06
     hormonal
    -0.06
     tanks
    -0.06
     cot
    -0.06
    wort
    -0.06
     creeping
    -0.06
    &eacute
    -0.06
     trauma
    -0.06
    -aff
    -0.06
     wrote
    -0.06
    POSITIVE LOGITS
     Vị
    0.07
     самом
    0.07
    .cache
    0.06
     Codec
    0.06
     paramString
    0.06
     unconstitutional
    0.06
     tuned
    0.06
     втор
    0.06
     Colour
    0.06
     dudes
    0.06
    Act Density 0.000%

    No Known Activations