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

    Neuronpedia

    INDEX
    Explanations

    _type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     excessively
    -0.07
    敷
    -0.07
    ℃
    -0.07
    .Redis
    -0.07
    快速
    -0.07
     moist
    -0.07
    高职
    -0.07
     retrospective
    -0.06
    Remote
    -0.06
     Expo
    -0.06
    POSITIVE LOGITS
    (filters
    0.07
    って
    0.07
    (label
    0.07
     văn
    0.07
     ;↵↵↵
    0.07
    总的来说
    0.07
     proprietà
    0.07
     atrav
    0.07
    ꒪
    0.06
     Sort
    0.06
    Act Density 0.000%

    No Known Activations