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

    Neuronpedia

    INDEX
    Explanations

    lab/laboratory/labrador related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    न
    0.98
    บั
    0.88
    ρθ
    0.87
    නු
    0.86
    le
    0.85
     tén
    0.85
    Auch
    0.85
    দে
    0.85
    एस
    0.84
     прос
    0.83
    POSITIVE LOGITS
    rador
    1.58
    ATORY
    1.39
    ו
    1.24
    atory
    1.18
    VIEW
    1.09
    itory
    1.03
    bered
    1.02
    ẳ
    1.00
    rinth
    0.99
    YR
    0.98
    Act Density 0.054%

    No Known Activations