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

    Neuronpedia

    INDEX
    Explanations

    healthy eating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Build
    -0.07
     Briggs
    -0.07
     Antar
    -0.07
     Mercer
    -0.06
    Heroes
    -0.06
     νο
    -0.06
    esát
    -0.06
    OfDay
    -0.06
     уровне
    -0.06
    機能
    -0.06
    POSITIVE LOGITS
    ensive
    0.07
     raft
    0.06
    acf
    0.06
    공
    0.06
     tossed
    0.06
    援
    0.06
     assaulted
    0.06
    ाध
    0.06
     interfaces
    0.06
     sk
    0.06
    Act Density 0.009%

    No Known Activations