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

    Neuronpedia

    INDEX
    Explanations

    text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pol
    -0.06
     reassure
    -0.06
    Cancelled
    -0.06
     refere
    -0.06
    gies
    -0.06
    addColumn
    -0.06
    енню
    -0.06
    alerts
    -0.06
    adastro
    -0.06
    isayar
    -0.06
    POSITIVE LOGITS
     ship
    0.07
     shack
    0.06
    ி
    0.06
    (audio
    0.06
    (spec
    0.06
     disappear
    0.06
    詩
    0.06
     ships
    0.06
    يب
    0.06
    νει
    0.06
    Act Density 0.000%

    No Known Activations