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

    Neuronpedia

    INDEX
    Explanations

    main office

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Eg
    0.87
    În
    0.77
    مة
    0.76
     множество
    0.75
    ारी
    0.75
    None
    0.75
     censure
    0.74
    比
    0.74
     正規
    0.74
    рав
    0.73
    POSITIVE LOGITS
    テナンス
    1.67
    AxisAlignment
    1.57
    stays
    1.52
    tained
    1.40
    AxisSize
    1.39
    tains
    1.36
    tenir
    1.19
    ifest
    1.12
    lobe
    1.10
    tenance
    1.05
    Act Density 0.179%

    No Known Activations