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

    Neuronpedia

    INDEX
    Explanations

    excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .network
    -0.08
    gmail
    -0.07
    염
    -0.07
    $$$
    -0.07
     hotspot
    -0.07
    .controls
    -0.07
    .addTarget
    -0.07
    )|(
    -0.07
    .lists
    -0.07
    stable
    -0.07
    POSITIVE LOGITS
    legen
    0.07
     Medic
    0.07
    粱
    0.07
     cyclic
    0.06
    =len
    0.06
    hya
    0.06
     leukemia
    0.06
     eg
    0.06
    Vac
    0.06
     revelations
    0.06
    Act Density 0.084%

    No Known Activations