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

    Neuronpedia

    INDEX
    Explanations

    regex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     '".$
    -0.07
    >{$
    -0.07
     telefon
    -0.06
     undefined
    -0.06
    ังกล
    -0.06
    tul
    -0.06
     Tri
    -0.06
     flo
    -0.06
     Kod
    -0.06
    POSITIVE LOGITS
    #[
    0.08
    รม
    0.07
     #[
    0.06
     Took
    0.06
    Lead
    0.06
     sucks
    0.06
     Sean
    0.06
     Ελλην
    0.06
     白
    0.06
    [OF
    0.06
    Act Density 0.023%

    No Known Activations