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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    buz
    -0.07
     Dez
    -0.07
    .Account
    -0.07
    pare
    -0.07
     pagamento
    -0.06
    Football
    -0.06
     opera
    -0.06
     agli
    -0.06
    poz
    -0.06
     beds
    -0.06
    POSITIVE LOGITS
    nesota
    0.08
     bladder
    0.07
    Rent
    0.07
     leave
    0.07
    Tr
    0.06
    fiber
    0.06
     tarihli
    0.06
    action
    0.06
    ்
    0.06
    렌
    0.06
    Act Density 0.000%

    No Known Activations