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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing difficulty or ability

    oai_token-act-pair · gemini-2.0-flash

    difficulty

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RegistryLite
    -0.62
    gnore
    -0.56
    primaryStage
    -0.50
     Reconnaissance
    -0.50
     Concentration
    -0.49
    rak
    -0.49
    sief
    -0.48
     savez
    -0.48
     Himalayan
    -0.47
     Pigment
    -0.47
    POSITIVE LOGITS
     difficult
    1.03
     hard
    0.97
    difficult
    0.90
     hardest
    0.83
     harder
    0.82
    Difficult
    0.81
     Difficult
    0.81
    hard
    0.80
    Hard
    0.79
     moeilijk
    0.76
    Act Density 0.406%

    No Known Activations