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

    Neuronpedia

    INDEX
    Explanations

    interrogative phrases and questions

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

    Question words (what, how, why, who)

    np_acts-logits-general · gemini-2.0-flash

    question words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Италијани
    -0.72
    /*
    -0.70
     تانيه
    -0.60
    fjspx
    -0.60
     **/
    -0.60
    }],
    -0.60
    })*/
    -0.59
     nakalista
    -0.59
     **)
    -0.58
    存于互联网档案馆
    -0.58
    POSITIVE LOGITS
     What
    0.67
    What
    0.67
     Welche
    0.65
    How
    0.63
     How
    0.62
     Quelles
    0.56
     ¿
    0.56
     Why
    0.52
     nedir
    0.50
    ¿
    0.50
    Act Density 0.560%

    No Known Activations