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

    Neuronpedia

    INDEX
    Explanations

    fire together

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jederzeit
    0.43
    variant
    0.38
     கொள்
    0.38
     Params
    0.38
    枚举
    0.37
     могат
    0.37
     finit
    0.36
    Labs
    0.36
     제도
    0.36
     chahiye
    0.36
    POSITIVE LOGITS
     materiality
    0.41
    retirement
    0.40
    পদ
    0.36
    ဆ
    0.36
    鶚
    0.35
     Tanaka
    0.35
     purification
    0.35
    美味し
    0.35
    authentication
    0.35
     authentication
    0.34
    Act Density 0.003%

    No Known Activations