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

    Neuronpedia

    INDEX
    Explanations

    commands or reset

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     samma
    0.68
     vanilla
    0.67
     ∂
    0.65
     samme
    0.64
     newest
    0.64
     livro
    0.64
     gó
    0.63
     classiques
    0.63
     sponsoring
    0.62
     arxiv
    0.62
    POSITIVE LOGITS
    Reset
    0.83
    deviceName
    0.80
    Logout
    0.78
    GPIO
    0.76
    UNLOCK
    0.75
    DeviceId
    0.74
    RESET
    0.74
     Reset
    0.73
     RESET
    0.73
    reset
    0.72
    Act Density 0.000%

    No Known Activations