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

    Neuronpedia

    INDEX
    Explanations

    concepts related to policy, social issues, or political commentary

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

    Mathematical or logical connectors

    np_acts-logits-general · gemini-2.0-flash

    listing and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    saraba
    -0.71
     CommandType
    -0.65
    __":
    -0.63
    >*/
    -0.61
     pope
    -0.59
     noro
    -0.58
    __":
    -0.58
     DBNull
    -0.57
     Профиль
    -0.55
    gemeente
    -0.54
    POSITIVE LOGITS
     diantaranya
    0.74
     didalam
    0.71
     diatas
    0.65
     Вас
    0.64
     Real
    0.63
     Juifs
    0.60
     idag
    0.60
     Вам
    0.59
     Right
    0.58
     Vám
    0.58
    Act Density 0.356%

    No Known Activations