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

    Neuronpedia

    INDEX
    Explanations

    UI layout elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     önlem
    -0.07
     mind
    -0.06
     골
    -0.06
     deem
    -0.06
     ├
    -0.06
    高度
    -0.06
     neler
    -0.06
    (network
    -0.06
    -stars
    -0.06
     Zoe
    -0.06
    POSITIVE LOGITS
    bcrypt
    0.07
     cartoons
    0.07
    avored
    0.07
    interactive
    0.06
     amendment
    0.06
    ..↵
    0.06
     anos
    0.06
    super
    0.06
    ē
    0.06
     aud
    0.06
    Act Density 0.005%

    No Known Activations