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

    Neuronpedia

    INDEX
    Explanations

    annual statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _eq
    -0.07
    Cfg
    -0.07
    _lim
    -0.06
    ía
    -0.06
    ipe
    -0.06
    𝚏
    -0.06
     constexpr
    -0.06
    osg
    -0.06
    aja
    -0.06
    pz
    -0.06
    POSITIVE LOGITS
    =[]
↵
    0.07
    ⚗
    0.07
     yayın
    0.07
    党建工作
    0.07
     trabajo
    0.07
    联社
    0.07
     ранее
    0.07
     awakeFromNib
    0.07
     Empresa
    0.06
     Webcam
    0.06
    Act Density 0.091%

    No Known Activations