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

    Neuronpedia

    INDEX
    Explanations

    phrases with numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     strategies
    0.42
     cytology
    0.42
    Poor
    0.42
    ോഗ
    0.41
     tactics
    0.40
    積
    0.40
     estates
    0.39
    安い
    0.39
    strategies
    0.38
     মুজিবকে
    0.38
    POSITIVE LOGITS
     linha
    0.42
     hati
    0.40
    Lever
    0.39
     Com
    0.38
     Lever
    0.38
    readthedocs
    0.37
     Pan
    0.36
    ảo
    0.36
     leveraged
    0.36
     اما
    0.36
    Act Density 0.000%

    No Known Activations