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

    Neuronpedia

    INDEX
    Explanations

    words starting with ab

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bora
    0.73
    ワイン
    0.68
    贼
    0.68
    णाल
    0.67
     Rider
    0.67
    olian
    0.67
     Criterion
    0.66
     リュック
    0.66
    ការព
    0.66
     തിര
    0.65
    POSITIVE LOGITS
    Ab
    3.89
     Ab
    3.76
     ab
    3.74
     AB
    3.59
    AB
    3.42
     ABS
    3.40
    ab
    3.39
     abs
    3.29
    ABS
    3.19
     Аб
    3.15
    Act Density 0.036%

    No Known Activations