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
     Meadows
    -0.07
     default
    -0.07
     وضع
    -0.07
     Poster
    -0.06
     مون
    -0.06
     footsteps
    -0.06
     onların
    -0.06
     Abbott
    -0.06
     deja
    -0.06
     Voices
    -0.06
    POSITIVE LOGITS
    ு
    0.06
    -kit
    0.06
    ')
↵
↵
    0.06
    __)↵
    0.06
    -se
    0.06
    js
    0.06
    .fast
    0.06
    ":
↵
    0.06
    ':
↵
    0.06
     bel
    0.06
    Act Density 0.003%

    No Known Activations