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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kin
    -0.07
    には
    -0.07
    =dict
    -0.07
     lact
    -0.06
    fields
    -0.06
     Marcus
    -0.06
     materials
    -0.06
    ===========
    -0.06
     fashioned
    -0.06
    logradouro
    -0.06
    POSITIVE LOGITS
     communal
    0.06
    -aos
    0.06
     getResource
    0.06
    Pago
    0.06
    ────
    0.06
     ubyt
    0.06
     yeterli
    0.05
     fought
    0.05
     Ride
    0.05
     nef
    0.05
    Act Density 0.058%

    No Known Activations