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

    Neuronpedia

    INDEX
    Explanations

    need

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     afl
    -0.08
    ите
    -0.07
     hotels
    -0.07
    intro
    -0.06
     매매가
    -0.06
    avn
    -0.06
    &A
    -0.06
     Hond
    -0.06
    _RAM
    -0.06
     ArrayList
    -0.06
    POSITIVE LOGITS
     درون
    0.06
     dissolution
    0.06
    schemas
    0.06
    _cou
    0.06
     همه
    0.05
    eniz
    0.05
    ="<?=$
    0.05
    THOOK
    0.05
    ट
    0.05
     cleaners
    0.05
    Act Density 0.028%

    No Known Activations