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

    Neuronpedia

    INDEX
    Explanations

    receiving approval

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ิทยาล
    -0.07
    rays
    -0.06
     positioned
    -0.06
    ..."↵
    -0.06
    %↵
    -0.06
    ae
    -0.06
     vertices
    -0.06
    ?:
    -0.06
    lesc
    -0.06
    Що
    -0.06
    POSITIVE LOGITS
     blinded
    0.07
    SHOT
    0.07
    名無し
    0.06
    تماع
    0.06
     baş
    0.06
     conte
    0.06
     vog
    0.06
     flag
    0.06
     發
    0.06
    defaults
    0.06
    Act Density 0.046%

    No Known Activations