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

    Neuronpedia

    INDEX
    Explanations

    they

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     capacity
    -0.07
     obscene
    -0.07
    ))[
    -0.06
     інш
    -0.06
    Reducers
    -0.06
    EObject
    -0.06
     Stamford
    -0.06
    .DoesNotExist
    -0.06
    \Factories
    -0.06
    redential
    -0.06
    POSITIVE LOGITS
     yaml
    0.07
     Delay
    0.07
     &#
    0.06
    kowski
    0.06
     API
    0.06
    asi
    0.06
    佳
    0.06
    HEEL
    0.06
     ignor
    0.06
    APPED
    0.06
    Act Density 0.000%

    No Known Activations