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

    Neuronpedia

    INDEX
    Explanations

    statements of support or loyalty to individuals or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sole concentration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.80
     PeEnEo
    -0.71
     gyhoeddwyd
    -0.70
     themſelves
    -0.68
     itſelf
    -0.66
    ſelves
    -0.66
    UrlResolution
    -0.66
    Derbyniad
    -0.65
    цездатний
    -0.64
     Roskov
    -0.64
    POSITIVE LOGITS
     my
    0.46
    mys
    0.35
     My
    0.31
     hôm
    0.29
    my
    0.27
     I
    0.27
     stepping
    0.27
    Conclusiones
    0.26
     MY
    0.25
     mijn
    0.25
    Act Density 0.054%

    No Known Activations