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

    Neuronpedia

    INDEX
    Explanations

    sentiment indicating a positive review or experience

    oai_token-act-pair · gemini-2.0-flash

    experience

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     talk
    -0.53
     actionPerformed
    -0.50
     cref
    -0.50
    }\,
    -0.48
    帖最后由
    -0.48
     活
    -0.47
     {}),
    -0.46
    JMenuItem
    -0.46
    пок
    -0.45
    hö
    -0.45
    POSITIVE LOGITS
     experience
    1.66
     experiences
    1.60
    experience
    1.48
     Experience
    1.48
     EXPERIENCE
    1.48
    Experience
    1.47
     Experiences
    1.46
    experiences
    1.42
     expérience
    1.38
     experiencias
    1.28
    Act Density 1.479%

    No Known Activations