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

    Neuronpedia

    INDEX
    Explanations

    fragments of spoken conversation or inner monologue

    oai_token-act-pair · gemini-2.0-flash

    technical terms or programming concepts

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ]._
    -0.68
    <bos>
    -0.65
     維
    -0.60
     ?>/
    -0.59
    ertale
    -0.58
    Condol
    -0.58
     Faire
    -0.57
    "]=
    -0.57
    Versión
    -0.57
    Portale
    -0.57
    POSITIVE LOGITS
    DockStyle
    0.52
    AndEndTag
    0.46
    writeField
    0.45
     veu
    0.43
    ActionCreators
    0.43
    ksikon
    0.42
     FORGET
    0.42
    Enllaces
    0.42
     Forget
    0.41
     povezave
    0.41
    Act Density 1.847%

    No Known Activations