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

    Neuronpedia

    INDEX
    Explanations

    keywords that indicate actions or decision-making processes

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

    make a decision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gynhyrchwyd
    -0.57
    tvguidetime
    -0.56
    aarrggbb
    -0.50
     '\\;'
    -0.49
    Бахар
    -0.48
     ffilmiau
    -0.45
    énario
    -0.45
    camara
    -0.44
     ब्रेकडाउन
    -0.44
     Houſe
    -0.44
    POSITIVE LOGITS
     decided
    0.52
    decided
    0.43
     SqlCommand
    0.40
     решили
    0.39
     decidió
    0.39
     решил
    0.38
     particularly
    0.36
     particuli
    0.35
    Rüyada
    0.35
     решила
    0.35
    Act Density 0.065%

    No Known Activations