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

    Neuronpedia

    INDEX
    Explanations

    punctuation/brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pages
    -0.08
    Jennifer
    -0.07
    ::.
    -0.07
     moving
    -0.07
    ()
    -0.06
    ++;
↵
    -0.06
    Anyway
    -0.06
     printing
    -0.06
     marching
    -0.06
    裰
    -0.06
    POSITIVE LOGITS
    (Qt
    0.08
    的特点
    0.08
     Spaß
    0.07
     tox
    0.07
    zet
    0.07
    ῆ
    0.07
    .ma
    0.07
    (find
    0.07
    是国内
    0.06
    -es
    0.06
    Act Density 0.065%

    No Known Activations