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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ballet
    -0.07
     copies
    -0.07
     opat
    -0.07
    pleasant
    -0.06
    紅
    -0.06
    -down
    -0.06
    Echo
    -0.06
    اقع
    -0.06
     impacting
    -0.06
     Lean
    -0.06
    POSITIVE LOGITS
    .fn
    0.06
    �
    0.06
    jištění
    0.06
    .False
    0.06
     nga
    0.06
     họa
    0.06
    ิการ
    0.06
    '[
    0.06
     cwd
    0.06
    ORS
    0.06
    Act Density 0.024%

    No Known Activations