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

    Neuronpedia

    INDEX
    Explanations

    code with multiple dots and underscores

    oai_token-act-pair · gemini-2.0-flash

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -0.75
     purpoſe
    -0.65
    Tikang
    -0.64
     becauſe
    -0.62
     Majefty
    -0.60
     radium
    -0.60
    PageFactory
    -0.59
     myſelf
    -0.58
     pleaſure
    -0.58
     doubtnut
    -0.57
    POSITIVE LOGITS
    RegressionTest
    0.60
     T
    0.50
    endswith
    0.49
    ResumeLayout
    0.48
    
    0.47
     Great
    0.46
    :+:
    0.46
    исленность
    0.46
    글
    0.45
    '][]
    0.44
    Act Density 2.312%

    No Known Activations