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

    Neuronpedia

    INDEX
    Explanations

    twisted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .R
    -0.07
    股
    -0.07
    _ud
    -0.07
    OCUMENT
    -0.06
     danger
    -0.06
    .I
    -0.06
    🦉
    -0.06
    麥
    -0.06
    שקיע
    -0.06
     Sax
    -0.06
    POSITIVE LOGITS
     Arrest
    0.08
     diğer
    0.07
    ISO
    0.07
     Currently
    0.07
     Alloc
    0.07
     acting
    0.06
     Nẵ
    0.06
     Keller
    0.06
     Floors
    0.06
    _Node
    0.06
    Act Density 0.004%

    No Known Activations