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

    Neuronpedia

    INDEX
    Explanations

    let get too

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mein
    0.41
     imidazol
    0.40
    ズニー
    0.39
    ਫ
    0.38
    Subsec
    0.38
     Liebe
    0.38
     emocion
    0.38
    relativePath
    0.38
    燄
    0.37
    òn
    0.37
    POSITIVE LOGITS
    SAMPLE
    0.42
     নমুনা
    0.39
    VARIABLES
    0.38
     Powder
    0.36
     粉
    0.36
     bột
    0.35
    粉
    0.35
     tokenId
    0.34
     reparar
    0.34
     powder
    0.34
    Act Density 0.000%

    No Known Activations