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

    Neuronpedia

    INDEX
    Explanations

    Numbers and patent references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bennett
    -0.08
    <quote
    -0.08
    :{}
    -0.07
     Astroph
    -0.07
     Billy
    -0.07
    -band
    -0.07
    chor
    -0.07
    ’Brien
    -0.07
    numbers
    -0.07
    lower
    -0.06
    POSITIVE LOGITS
     seize
    0.06
    (profile
    0.06
     zas
    0.06
     vegan
    0.06
    ivating
    0.06
     slashing
    0.06
     روست
    0.06
    subscriptions
    0.06
     तह
    0.05
     PUS
    0.05
    Act Density 0.358%

    No Known Activations