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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    着
    -0.07
    ся
    -0.07
     towers
    -0.07
     Mov
    -0.07
     Holt
    -0.07
    шись
    -0.06
    ่าร
    -0.06
     bubbles
    -0.06
    *)((
    -0.06
     dis
    -0.06
    POSITIVE LOGITS
    πουλος
    0.07
    development
    0.06
    anggal
    0.06
    _ls
    0.06
     wannonce
    0.06
     rtn
    0.06
     xxx
    0.06
    ateway
    0.06
    ialog
    0.06
    /O
    0.06
    Act Density 0.030%

    No Known Activations