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

    Neuronpedia

    INDEX
    Explanations

    replace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lông
    -0.07
     Yar
    -0.07
     Reb
    -0.06
    941
    -0.06
     vej
    -0.06
    径
    -0.06
     Ree
    -0.06
    Für
    -0.06
    <object
    -0.06
    clave
    -0.06
    POSITIVE LOGITS
     Genuine
    0.07
    PHP
    0.06
    brates
    0.06
    <|begin_of_text|>
    0.06
     MIDI
    0.06
     macros
    0.06
     ем
    0.06
    -widgets
    0.06
    /ext
    0.06
     inters
    0.06
    Act Density 0.028%

    No Known Activations