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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    //
    -0.06
    CLAIM
    -0.06
     Ferrari
    -0.06
     Brett
    -0.06
     Deprecated
    -0.06
     survive
    -0.06
     revelations
    -0.06
     haste
    -0.06
    (compact
    -0.06
     využití
    -0.05
    POSITIVE LOGITS
    Conv
    0.08
    Sync
    0.07
    .nc
    0.06
     mon
    0.06
    开
    0.06
    biology
    0.06
    Carlos
    0.06
     sym
    0.06
     necklace
    0.06
    payer
    0.06
    Act Density 0.000%

    No Known Activations