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

    Neuronpedia

    INDEX
    Explanations

    JSON-like structured data elements or objects

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

    JSON-like syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſch
    -0.66
     ſche
    -0.66
     viſ
    -0.61
     Inſ
    -0.60
     preſent
    -0.59
     ſur
    -0.59
     ſtre
    -0.59
     ſec
    -0.59
     faſt
    -0.59
     laſt
    -0.58
    POSITIVE LOGITS
    },
    1.11
    '},
    0.77
     },
    0.74
    ]},
    0.70
     \%,
    0.69
    ()},
    0.69
    \},
    0.68
    },
    0.66
    )},
    0.66
    }},
    0.64
    Act Density 0.109%

    No Known Activations