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

    Neuronpedia

    INDEX
    Explanations

    references to commentary and responses in written text

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

    Numbers as the first element in a list

    np_acts-logits-general · gemini-2.0-flash

    numbered lists and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mag
    -0.59
     }}\
    -0.59
     }?>
    -0.59
     }}$.
    -0.55
     }}</
    -0.54
    PINES
    -0.54
    ]]
    -0.54
     ddelweddau
    -0.53
    Fonto
    -0.53
    VIAF
    -0.52
    POSITIVE LOGITS
     Infórmanos
    0.73
     виправивши
    0.68
    Personensuche
    0.67
    Hochspringen
    0.67
     متعلقه
    0.66
     Saltar
    0.63
     Drapeau
    0.62
     Pingback
    0.62
     дописавши
    0.61
    Enllaces
    0.60
    Act Density 0.027%

    No Known Activations