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

    Neuronpedia

    INDEX
    Explanations

    conversational filler and hedging language in opinionated statements

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hentet
    -0.47
    ots
    -0.47
     apostles
    -0.46
    jej
    -0.46
    chi
    -0.44
     прово
    -0.43
    not
    -0.43
    兆
    -0.43
     indeb
    -0.42
    devtools
    -0.42
    POSITIVE LOGITS
    tagHelperRunner
    0.66
    úsqueda
    0.60
    featureID
    0.60
    enumi
    0.59
    déric
    0.57
     Administrativna
    0.55
    casm
    0.55
    webElementGuid
    0.55
    <?
    0.54
     XXIV
    0.53
    Act Density 2.315%

    No Known Activations