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

    Neuronpedia

    INDEX
    Explanations

    transported

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -I
    -0.06
    άνα
    -0.06
     Feed
    -0.06
    Rank
    -0.06
    cient
    -0.06
     clerk
    -0.06
    Care
    -0.06
     incredible
    -0.06
    룹
    -0.06
     lith
    -0.06
    POSITIVE LOGITS
     sass
    0.07
    /org
    0.07
     μέσα
    0.06
     Links
    0.06
     Grim
    0.06
     recent
    0.06
    合わせ
    0.06
     Soda
    0.06
    GED
    0.06
     erot
    0.06
    Act Density 0.034%

    No Known Activations