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

    Neuronpedia

    INDEX
    Explanations

    programming questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xffffffff
    -0.07
    SuppressWarnings
    -0.07
    通り
    -0.06
    검
    -0.06
    Uno
    -0.06
    Da
    -0.06
     quelque
    -0.06
    resi
    -0.06
    крет
    -0.06
     Interracial
    -0.06
    POSITIVE LOGITS
     нап
    0.08
     Nap
    0.08
     напря
    0.08
     messing
    0.07
     Threat
    0.07
    (conn
    0.07
     Katie
    0.06
     Chim
    0.06
     Lamp
    0.06
     Noise
    0.06
    Act Density 0.002%

    No Known Activations