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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,,
    -0.06
     ".
    -0.06
     DO
    -0.06
    рай
    -0.06
    購
    -0.06
    acro
    -0.06
     -.
    -0.06
     indonesia
    -0.06
     Brand
    -0.06
     asian
    -0.05
    POSITIVE LOGITS
    cete
    0.07
     aquel
    0.06
    ]->
    0.06
    Founder
    0.06
    $options
    0.06
     땅
    0.06
    _rs
    0.06
    .hit
    0.06
    /window
    0.06
    .Option
    0.06
    Act Density 0.260%

    No Known Activations