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

    Neuronpedia

    INDEX
    Explanations

    app

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Anast
    -0.07
    bounds
    -0.07
    edl
    -0.07
     painters
    -0.07
    руч
    -0.07
     Mitarbeiter
    -0.07
     @"↵
    -0.07
    erguson
    -0.07
    보았다
    -0.07
    aker
    -0.06
    POSITIVE LOGITS
     neo
    0.07
     мат
    0.06
     pre
    0.06
     Simpl
    0.06
    进一步
    0.06
     pac
    0.06
     adopting
    0.06
    765
    0.06
     reminded
    0.06
     circum
    0.06
    Act Density 0.005%

    No Known Activations