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

    Neuronpedia

    INDEX
    Explanations

    Santos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     avalia
    -0.07
     arrivals
    -0.07
    autop
    -0.07
     weapon
    -0.06
     kvinne
    -0.06
     dönemin
    -0.06
     Patton
    -0.06
    pression
    -0.06
    année
    -0.06
    env
    -0.06
    POSITIVE LOGITS
    ,,,,
    0.08
    .instances
    0.07
    🖋
    0.07
     devis
    0.07
     /\
    0.07
     yeast
    0.07
     tedious
    0.07
    逑
    0.07
     //<
    0.07
     mim
    0.06
    Act Density 0.003%

    No Known Activations