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

    Neuronpedia

    INDEX
    Explanations

    population demographics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    棱
    -0.07
     לז
    -0.07
    하지
    -0.07
    妥善
    -0.07
    着眼
    -0.07
    得多
    -0.06
    _ng
    -0.06
    อาร
    -0.06
    洁净
    -0.06
    ToLeft
    -0.06
    POSITIVE LOGITS
    ilent
    0.08
    ائل
    0.08
     Scaffold
    0.08
    ::::::::
    0.07
     moistur
    0.07
     decorations
    0.07
     différents
    0.07
     marty
    0.07
    冻
    0.07
     relative
    0.07
    Act Density 0.048%

    No Known Activations