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

    Neuronpedia

    INDEX
    Explanations

    refrigerators/plasma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AndEndTag
    -1.10
    Hochspringen
    -1.03
     étoient
    -0.99
     NSCoder
    -0.99
    Vidite
    -0.94
     defaultstate
    -0.94
     avoient
    -0.94
     feroit
    -0.93
     enfans
    -0.93
     surla
    -0.93
    POSITIVE LOGITS
    <bos>
    0.79
     
    0.73
    ↵↵
    0.72
    ,
    0.70
     the
    0.69
    '
    0.68
    <strong>
    0.61
     (
    0.61
    /
    0.60
     and
    0.60
    Act Density 0.059%

    No Known Activations