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

    Neuronpedia

    INDEX
    Explanations

    Narrowing down choices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    離
    -0.07
    pler
    -0.07
     noqa
    -0.07
     achievements
    -0.07
    假的
    -0.07
    687
    -0.07
     ioe
    -0.07
    lässlich
    -0.07
     вій
    -0.07
     championships
    -0.07
    POSITIVE LOGITS
     lựa
    0.14
     후보
    0.13
    Candidates
    0.13
     પસંદ
    0.13
     ఎంప
    0.12
     shortlisted
    0.12
     నిర్ణ
    0.12
    _candidates
    0.12
    Choosing
    0.12
     выбран
    0.12
    Act Density 0.098%

    No Known Activations