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

    Neuronpedia

    INDEX
    Explanations

    Code-related questions/answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eventual
    -0.07
     Serum
    -0.06
     pinch
    -0.06
    share
    -0.06
     کن
    -0.06
     comforts
    -0.06
    Wrapped
    -0.06
     før
    -0.06
    }else
    -0.06
    xygen
    -0.06
    POSITIVE LOGITS
     лікар
    0.06
    cke
    0.06
    _MAIL
    0.06
    ARS
    0.06
    ählen
    0.06
     mund
    0.06
    织
    0.06
     Phật
    0.06
     DRAW
    0.06
     клі
    0.06
    Act Density 0.047%

    No Known Activations