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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Religious
    -0.07
    _daily
    -0.07
     Musk
    -0.07
    CTest
    -0.07
     hazardous
    -0.07
     androidx
    -0.06
    inecraft
    -0.06
     Senator
    -0.06
     petitions
    -0.06
     Españ
    -0.06
    POSITIVE LOGITS
    ’ı
    0.07
    保护
    0.07
     із
    0.06
    oser
    0.06
    ॉट
    0.06
    ivable
    0.06
     drawer
    0.06
    slideDown
    0.06
     відч
    0.06
    Ф
    0.06
    Act Density 0.055%

    No Known Activations