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

    Neuronpedia

    INDEX
    Explanations

    debugger tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rection
    0.44
     testim
    0.44
    Inspect
    0.42
    таны
    0.40
    ternal
    0.40
    ortal
    0.40
    Export
    0.39
    tbl
    0.39
     file
    0.39
    Analysis
    0.39
    POSITIVE LOGITS
     लॉन्
    0.44
    神经
    0.43
     стандарт
    0.41
    LLDB
    0.40
     Lancet
    0.40
     estándar
    0.39
     launched
    0.39
     Launcher
    0.38
     Goodreads
    0.38
     launches
    0.38
    Act Density 0.003%

    No Known Activations