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

    Neuronpedia

    INDEX
    Explanations

    amongst

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    िक
    1.42
     протягом
    1.31
     Each
    1.25
    𝙖
    1.20
     يكون
    1.15
     jeweil
    1.14
     каждый
    1.14
    في
    1.13
    𝙩
    1.12
    𝙣
    1.12
    POSITIVE LOGITS
     annet
    1.65
    śród
    1.61
    народ
    1.56
    maßen
    1.54
     andet
    1.53
    зем
    1.49
    et
    1.48
    ר
    1.44
    serrat
    1.43
     peers
    1.43
    Act Density 0.014%

    No Known Activations