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

    Neuronpedia

    INDEX
    Explanations

    world built

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ig
    0.45
     U
    0.44
    向下
    0.44
    "]]
    0.44
     нему
    0.43
     discontent
    0.41
     C
    0.41
    OV
    0.41
     P
    0.40
     নিজেদের
    0.40
    POSITIVE LOGITS
     febru
    0.49
    斯的
    0.49
     presque
    0.49
    PTMR
    0.49
    🥯
    0.49
    砣
    0.47
    當
    0.47
    emption
    0.46
    credibly
    0.46
    YLE
    0.46
    Act Density 0.003%

    No Known Activations