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

    Neuronpedia

    INDEX
    Explanations

    Protests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (public
    -0.07
    illator
    -0.06
    πι
    -0.06
    usic
    -0.06
    .Site
    -0.06
    (Document
    -0.06
     diferentes
    -0.06
    Shortcut
    -0.06
     CEO
    -0.06
     shirt
    -0.06
    POSITIVE LOGITS
     prejudices
    0.07
     місця
    0.06
     CVE
    0.06
    ください
    0.06
     unfore
    0.06
     glVertex
    0.06
    させる
    0.06
     WN
    0.06
    .gr
    0.06
     같습니다
    0.06
    Act Density 0.016%

    No Known Activations