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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions of mechanisms and their components

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thing
    -0.57
     bag
    -0.54
     calculées
    -0.52
    mannian
    -0.51
    ikkert
    -0.50
    IContainer
    -0.50
    amycin
    -0.49
     THING
    -0.49
     Wrapper
    -0.48
     her
    -0.48
    POSITIVE LOGITS
    rungsseite
    0.73
     AssemblyVersion
    0.68
     ་་
    0.68
     QH
    0.68
     Cæsar
    0.67
     houſe
    0.67
     Houſe
    0.66
     Viceroy
    0.66
     noft
    0.63
     pouvoit
    0.63
    Act Density 0.115%

    No Known Activations