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

    Neuronpedia

    INDEX
    Explanations

    regular expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     podrían
    0.43
    C
    0.42
    Claude
    0.42
    ร
    0.41
     fournir
    0.41
    addTask
    0.40
    ലീസ്
    0.40
     foothills
    0.40
    หา
    0.39
    Sharing
    0.39
    POSITIVE LOGITS
    дзі
    0.47
    ikten
    0.46
    akov
    0.46
     정확
    0.45
    的地
    0.45
    jeg
    0.44
    𒈾
    0.44
     وقت
    0.44
    ⠀⠀
    0.43
    意识
    0.43
    Act Density 0.005%

    No Known Activations