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

    Neuronpedia

    INDEX
    Explanations

    win or loss predictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jeśli
    0.41
    瑾
    0.41
     indium
    0.39
    crystalline
    0.39
    浏览器
    0.38
    ጴ
    0.38
    泷
    0.37
    nętr
    0.37
     চৈত
    0.36
    ྪ
    0.36
    POSITIVE LOGITS
     outsiders
    0.43
     rivalry
    0.42
     revenge
    0.41
     revanche
    0.39
     amateurs
    0.38
     moeilijk
    0.37
     comrades
    0.37
     demoral
    0.37
     victory
    0.36
    club
    0.36
    Act Density 0.000%

    No Known Activations