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

    Neuronpedia

    INDEX
    Explanations

    numerical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thirst
    -0.07
     trä
    -0.07
    할
    -0.07
     Serialize
    -0.06
     خی
    -0.06
    oader
    -0.06
     名
    -0.06
     provider
    -0.06
     },↵↵↵
    -0.06
    /conf
    -0.06
    POSITIVE LOGITS
     zwarte
    0.07
     mijn
    0.06
    _SOC
    0.06
     Nebraska
    0.06
    damn
    0.06
     snag
    0.06
     uyum
    0.06
    .ContentAlignment
    0.06
     준
    0.06
     الولايات
    0.06
    Act Density 0.031%

    No Known Activations