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

    Neuronpedia

    INDEX
    Explanations

    errors in grammar, spelling, and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nut
    0.45
    其它
    0.44
    畜
    0.40
     appreciable
    0.40
    ¼
    0.39
    綵
    0.39
    esters
    0.38
    柔软
    0.38
    ред
    0.37
    ills
    0.37
    POSITIVE LOGITS
    *:
    0.56
    +:
    0.49
     Boeing
    0.47
     zuerst
    0.47
     Discovery
    0.46
    \":
    0.46
    }:
    0.45
     Starter
    0.45
     ':
    0.45
     Aviation
    0.44
    Act Density 0.005%

    No Known Activations