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

    Neuronpedia

    INDEX
    Explanations

    outline, summary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
     hmm
    -0.08
     보다
    -0.08
     �
    -0.08
     оказалось
    -0.08
     ???↵↵
    -0.08
     entraî
    -0.08
     ?>"
    -0.08
    CY
    -0.08
    ಂಟ್
    -0.08
    POSITIVE LOGITS
     approximate
    0.08
     asas
    0.07
     प्रत्येक
    0.07
    warming
    0.07
     thoroughly
    0.07
     كيف
    0.07
    سس
    0.07
     saying
    0.07
    četně
    0.07
    şı
    0.07
    Act Density 0.194%

    No Known Activations