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

    Neuronpedia

    INDEX
    Explanations

    Code/unformatted text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.07
    _binding
    -0.07
     LY
    -0.06
    tection
    -0.06
    Hang
    -0.06
    .getList
    -0.06
     compound
    -0.06
    dling
    -0.06
    -depth
    -0.06
     pioneered
    -0.06
    POSITIVE LOGITS
     lubric
    0.07
     pode
    0.06
    责
    0.06
    袖
    0.06
     จะ
    0.06
    ленні
    0.06
     comet
    0.06
     anyone
    0.06
     بهبود
    0.06
     Docs
    0.06
    Act Density 0.000%

    No Known Activations