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

    Neuronpedia

    INDEX
    Explanations

    Code/text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -described
    -0.08
    aran
    -0.07
    rips
    -0.07
     �
    -0.07
     caves
    -0.06
    ють
    -0.06
    hů
    -0.06
    ابق
    -0.06
     điểm
    -0.06
    яв
    -0.06
    POSITIVE LOGITS
    Honda
    0.07
    OrNull
    0.07
     سخت
    0.06
     yum
    0.06
     dvoj
    0.06
    =end
    0.06
    "}↵
    0.06
     Honda
    0.06
     @{$
    0.06
     plá
    0.06
    Act Density 0.000%

    No Known Activations