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

    Neuronpedia

    INDEX
    Explanations

    computer interface interaction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exclaimed
    -0.07
    emmel
    -0.06
     deux
    -0.06
    .Invariant
    -0.06
     MX
    -0.06
     louis
    -0.06
    .Col
    -0.06
    plaintext
    -0.06
    _SIGNAL
    -0.06
     setStatus
    -0.06
    POSITIVE LOGITS
    (reordered
    0.08
    dns
    0.07
    571
    0.06
    ocket
    0.06
    UNS
    0.06
     топ
    0.06
    (strings
    0.06
    智
    0.06
    บท
    0.06
     %@",
    0.06
    Act Density 0.047%

    No Known Activations