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

    Neuronpedia

    INDEX
    Explanations

    six

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pens
    -0.08
    sla
    -0.07
     menace
    -0.07
    hma
    -0.07
     IPA
    -0.06
    舍
    -0.06
    凝
    -0.06
     الرح
    -0.06
     faker
    -0.06
     따라
    -0.06
    POSITIVE LOGITS
     Every
    0.07
    Installing
    0.07
    JsonObject
    0.06
    TEL
    0.06
     STDERR
    0.06
    ialias
    0.06
     Soup
    0.06
    Kind
    0.06
    February
    0.06
     Unlike
    0.06
    Act Density 0.000%

    No Known Activations