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

    Neuronpedia

    INDEX
    Explanations

    Pros and cons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Quickly
    -0.07
     Hancock
    -0.07
     Naughty
    -0.07
     farther
    -0.07
    힌
    -0.07
    argout
    -0.06
    .Script
    -0.06
    쳉
    -0.06
     Applicant
    -0.06
     Apparently
    -0.06
    POSITIVE LOGITS
    `='$
    0.07
     surf
    0.07
    anos
    0.07
     mở
    0.07
    celona
    0.07
    酡
    0.07
     idle
    0.07
    ⼈
    0.07
    Uri
    0.07
    Files
    0.06
    Act Density 0.042%

    No Known Activations