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

    Neuronpedia

    INDEX
    Explanations

    terms related to project evaluation and intervention effectiveness

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

    study design and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.63
     nakalista
    -0.61
    :✨
    -0.59
    stdc
    -0.57
    hyrchwyd
    -0.54
     препратки
    -0.53
     кӀош
    -0.47
    GEBURTSDATUM
    -0.47
    /**/*.
    -0.46
    Jeografia
    -0.46
    POSITIVE LOGITS
     pauvreté
    0.41
     AssemblyCompany
    0.40
     bapak
    0.40
     barres
    0.40
     learners
    0.39
     perles
    0.39
     autobuses
    0.38
     USAID
    0.38
    -------
    0.38
    ngths
    0.37
    Act Density 0.182%

    No Known Activations