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

    Neuronpedia

    INDEX
    Explanations

    Data analysis and languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ft
    -0.08
     Oral
    -0.08
     resort
    -0.08
     resorts
    -0.08
     Resorts
    -0.08
     Resort
    -0.07
    さん
    -0.07
    条例
    -0.07
     oral
    -0.07
    _and
    -0.07
    POSITIVE LOGITS
    BAC
    0.09
    ৫
    0.08
    াস
    0.08
    母
    0.08
    �
    0.08
     hemp
    0.08
    bac
    0.08
    য়
    0.07
    няў
    0.07
     прошлом
    0.07
    Act Density 0.189%

    No Known Activations