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

    Neuronpedia

    INDEX
    Explanations

    sentiments around enjoyment and motivation in tasks

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

    enjoyment and fear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parency
    -0.41
     bambú
    -0.40
     Gauthier
    -0.39
     Metropolitana
    -0.37
     soundness
    -0.37
     Beweis
    -0.37
    curacies
    -0.37
    ControllerAdvice
    -0.37
    letzt
    -0.36
     zwró
    -0.36
    POSITIVE LOGITS
     Италијани
    0.53
     comuniques
    0.47
     pleaſure
    0.47
    دانشنامهٔ
    0.47
    sidemargin
    0.47
    SequentialGroup
    0.45
     kaarangay
    0.45
     كومونز
    0.43
    хьтан
    0.43
    ANTLR
    0.42
    Act Density 0.046%

    No Known Activations