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

    Neuronpedia

    INDEX
    Explanations

    media reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.06
    -solving
    -0.06
     Flush
    -0.06
     showroom
    -0.06
    ackages
    -0.06
    <th
    -0.06
    ่าท
    -0.06
    -0.06
     =================================================
    -0.06
     kingdom
    -0.06
    POSITIVE LOGITS
    osas
    0.07
    (entry
    0.07
    ennai
    0.06
    _authentication
    0.06
    hir
    0.06
    _clients
    0.06
    [text
    0.06
     adalah
    0.06
    イド
    0.06
     STACK
    0.06
    Act Density 0.019%

    No Known Activations