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

    Neuronpedia

    INDEX
    Explanations

    GUIDs and hyphenated IDs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fijn
    0.42
     goû
    0.40
     :}
    0.38
    শংস
    0.38
    ಿಸಬಹುದು
    0.38
    ycling
    0.37
    বত
    0.37
    肛
    0.36
     ぞ
    0.36
    ্বন
    0.36
    POSITIVE LOGITS
    -
    0.44
    comment
    0.37
     Illumin
    0.35
     Pacific
    0.35
    leeve
    0.35
     شوید
    0.35
     Vivid
    0.35
     Registry
    0.34
     comment
    0.34
     Reagan
    0.34
    Act Density 0.004%

    No Known Activations