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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     InternalEnumerator
    -0.07
    regs
    -0.07
    edException
    -0.06
     rich
    -0.06
     IST
    -0.06
     DOC
    -0.06
     самого
    -0.06
    811
    -0.06
    _attach
    -0.06
     shell
    -0.06
    POSITIVE LOGITS
     Four
    0.08
    ashi
    0.07
    Four
    0.07
     Filtering
    0.06
    Three
    0.06
    ляти
    0.06
    ві
    0.06
    Six
    0.06
     Thankfully
    0.06
     Six
    0.06
    Act Density 0.021%

    No Known Activations