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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ством
    -0.07
     المو
    -0.07
    птом
    -0.07
    Command
    -0.07
     materials
    -0.07
     material
    -0.07
    (res
    -0.06
    Descending
    -0.06
     triangle
    -0.06
    ophone
    -0.06
    POSITIVE LOGITS
    081
    0.07
    331
    0.06
     aes
    0.06
     уча
    0.06
     शत
    0.06
     reun
    0.06
     боя
    0.06
    349
    0.06
     Fiat
    0.06
     Accident
    0.06
    Act Density 0.021%

    No Known Activations