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

    Neuronpedia

    INDEX
    Explanations

    engu

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    From
    -0.06
    Care
    -0.06
    xi
    -0.06
    488
    -0.06
    IOS
    -0.06
    ены
    -0.06
    vae
    -0.06
    ternet
    -0.06
    About
    -0.06
    Proc
    -0.06
    POSITIVE LOGITS
    _ut
    0.07
     cunning
    0.06
    ‌ال
    0.06
    _AUD
    0.06
    .TH
    0.06
     regex
    0.06
    autorelease
    0.06
    руш
    0.06
    _Min
    0.06
     �
    0.06
    Act Density 0.004%

    No Known Activations