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

    Neuronpedia

    INDEX
    Explanations

    ai

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EURO
    -0.08
     assumed
    -0.07
     preferably
    -0.06
     Shaman
    -0.06
     genders
    -0.06
     Lau
    -0.06
     explic
    -0.06
    Sup
    -0.06
     Crack
    -0.06
    078
    -0.06
    POSITIVE LOGITS
    ai
    0.08
    _di
    0.07
     overdose
    0.07
     TextArea
    0.07
    AI
    0.07
     accountability
    0.07
     fitness
    0.06
     olmadı
    0.06
    ячи
    0.06
     tie
    0.06
    Act Density 0.001%

    No Known Activations