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

    Neuronpedia

    INDEX
    Explanations

    IO exceptions and reading operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     escorted
    0.37
     चैप्टर्स
    0.36
    acious
    0.35
     আক্রম
    0.35
     oznacza
    0.35
    rektor
    0.34
    ateness
    0.34
    ifference
    0.34
     besieged
    0.33
    othelium
    0.33
    POSITIVE LOGITS
     改
    0.34
    InputStream
    0.33
    ก
    0.33
    Exception
    0.32
     ê
    0.32
     Shader
    0.32
     Streaming
    0.31
     Incorrect
    0.31
    Parser
    0.31
    Tokenizer
    0.31
    Act Density 0.000%

    No Known Activations