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

    Neuronpedia

    INDEX
    Explanations

    references to hidden activities or behind-the-scenes situations

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

    behind the scenes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     feroit
    -0.52
     Italijani
    -0.52
     auroit
    -0.50
     doprav
    -0.49
     avoient
    -0.46
     pouvoit
    -0.45
     Gedicht
    -0.45
     mangá
    -0.44
    səhifə
    -0.44
     vícti
    -0.43
    POSITIVE LOGITS
     backstage
    1.16
    behind
    0.88
     Behind
    0.86
    Behind
    0.84
     BEHIND
    0.84
     behind
    0.83
    scenes
    0.69
     dietro
    0.65
     insider
    0.64
     detrás
    0.63
    Act Density 0.004%

    No Known Activations