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

    Neuronpedia

    INDEX
    Explanations

    certainty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sales
    -0.08
    _nick
    -0.07
    Josh
    -0.07
    “He
    -0.07
     Books
    -0.07
     nao
    -0.07
    _expr
    -0.07
     marry
    -0.06
    339
    -0.06
    鸟
    -0.06
    POSITIVE LOGITS
     uncertain
    0.11
     uncertainty
    0.10
     uncert
    0.08
     Ukraine
    0.07
     uncertainties
    0.07
     Hurricane
    0.07
     Ec
    0.07
    ُم
    0.07
     умови
    0.07
     silver
    0.06
    Act Density 0.005%

    No Known Activations