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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (save
    -0.07
     Rox
    -0.07
    .Diagnostics
    -0.06
     youthful
    -0.06
     tercih
    -0.06
     дет
    -0.06
     lowes
    -0.06
     rv
    -0.06
     visita
    -0.06
     шкі
    -0.06
    POSITIVE LOGITS
    jom
    0.08
    observation
    0.07
     Lewis
    0.07
    modation
    0.06
    át
    0.06
    modern
    0.06
    ££
    0.06
    Prosec
    0.06
    ProcAddress
    0.06
     MO
    0.06
    Act Density 0.003%

    No Known Activations