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

    Neuronpedia

    INDEX
    Explanations

    insistence and alternatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .display
    -0.06
    cision
    -0.06
    -gay
    -0.06
    arter
    -0.06
    िह
    -0.06
    ellung
    -0.06
    offline
    -0.06
    .documentation
    -0.06
    -League
    -0.06
     told
    -0.06
    POSITIVE LOGITS
     """↵
    0.07
     Beginner
    0.06
     Tian
    0.06
     Desert
    0.06
    eti
    0.06
    /projects
    0.06
     endorsements
    0.06
    '){
↵
    0.06
     acquire
    0.06
     국민
    0.06
    Act Density 0.013%

    No Known Activations