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

    Neuronpedia

    INDEX
    Explanations

    Code/legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    經濟
    -0.07
     sürecin
    -0.07
    atura
    -0.06
     rebuild
    -0.06
    flow
    -0.06
     Lawrence
    -0.06
     Harris
    -0.06
    compare
    -0.06
    式
    -0.06
    ocos
    -0.06
    POSITIVE LOGITS
    فائ
    0.08
     הב
    0.07
    ?\
    0.07
    꺄
    0.07
     NSUInteger
    0.07
    0.07
    Introduction
    0.07
     ControllerBase
    0.07
    ሀ
    0.07
    getField
    0.06
    Act Density 0.214%

    No Known Activations