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

    Neuronpedia

    INDEX
    Explanations

    Final Answer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fanciful
    0.40
    логов
    0.37
     retort
    0.37
     amending
    0.36
    меч
    0.36
    ொ
    0.36
     cups
    0.34
    naph
    0.34
    مثل
    0.34
    Stations
    0.34
    POSITIVE LOGITS
     Kern
    0.56
     Kernel
    0.46
    Kern
    0.46
    𝘆
    0.46
    KERNEL
    0.44
     WRITE
    0.38
    kernel
    0.37
     kernels
    0.37
     জনগণ
    0.37
     فرن
    0.37
    Act Density 0.001%

    No Known Activations