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

    Neuronpedia

    INDEX
    Explanations

    questions and inquiries related to evaluation or assessment

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

    questions and auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.77
     nakalista
    -0.73
     Италијани
    -0.65
    /*
    -0.64
    RTLR
    -0.60
    .*")]
    -0.60
     تانيه
    -0.56
     <<<<<<<<<<<<<<
    -0.56
    makeConstraints
    -0.55
    oredCriteria
    -0.55
    POSITIVE LOGITS
     Welche
    0.47
     assin
    0.40
    guém
    0.39
     Quelles
    0.39
     What
    0.39
     How
    0.39
     vieill
    0.37
     Apakah
    0.36
     ¿
    0.36
     nedir
    0.36
    Act Density 0.186%

    No Known Activations