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

    Neuronpedia

    INDEX
    Explanations

    directions/positions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Spider
    -0.06
    gro
    -0.06
     bytearray
    -0.06
    /repos
    -0.06
    Dry
    -0.06
    \S
    -0.06
    ★
    -0.06
    yang
    -0.06
    ,line
    -0.06
    Bern
    -0.06
    POSITIVE LOGITS
     sağlıklı
    0.07
     Target
    0.07
    e
    0.06
    gı
    0.06
     Lafayette
    0.06
     Illegal
    0.06
     Dell
    0.06
    adní
    0.06
     discoveries
    0.06
    _tick
    0.06
    Act Density 0.011%

    No Known Activations