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

    Neuronpedia

    INDEX
    Explanations

    code/definition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vương
    -0.07
    (er
    -0.07
    备
    -0.07
     freder
    -0.07
     trek
    -0.07
     Satellite
    -0.06
    .fname
    -0.06
     INCIDENT
    -0.06
     Rek
    -0.06
    degrees
    -0.06
    POSITIVE LOGITS
     memorable
    0.06
    ise
    0.06
    pets
    0.06
    listening
    0.06
    ivery
    0.06
     want
    0.06
     nev
    0.06
     imshow
    0.06
     afar
    0.06
     Love
    0.06
    Act Density 0.000%

    No Known Activations