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

    Neuronpedia

    INDEX
    Explanations

    personal experiences and references to family dynamics or relationships

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

    before a comma or quote

    np_acts-logits-general · gemini-2.0-flash

    foreign languages and time words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.60
    GeneratedMessage
    -0.53
    ]]
    -0.52
    }-*/;
    -0.52
    AndEndTag
    -0.52
    LElement
    -0.50
    transQ
    -0.50
    󠁧
    -0.50
    }>;
    -0.49
     ")";
    -0.49
    POSITIVE LOGITS
     direito
    0.42
     allora
    0.41
     tomorrow
    0.40
     entonces
    0.40
     crap
    0.40
     sekarang
    0.40
     maintenant
    0.39
     ahora
    0.39
     now
    0.38
     fijo
    0.38
    Act Density 0.349%

    No Known Activations