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

    Neuronpedia

    INDEX
    Explanations

    chart

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     segue
    -0.06
    Fight
    -0.06
     CLIENT
    -0.06
    Le
    -0.06
     Dj
    -0.06
     matte
    -0.06
    Sig
    -0.06
     Fight
    -0.06
    /Peak
    -0.06
     Fog
    -0.06
    POSITIVE LOGITS
    =[],
    0.07
     참고
    0.06
    لاین
    0.06
    compute
    0.06
    Exists
    0.06
    >'↵
    0.06
    용
    0.06
    "\↵
    0.06
    層
    0.06
     refin
    0.06
    Act Density 0.028%

    No Known Activations