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

    Neuronpedia

    INDEX
    Explanations

    "lib" followed by software components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    timmt
    -1.97
     those
    -1.91
     Makes
    -1.84
    琹
    -1.80
     lebte
    -1.79
    釙
    -1.76
     gehörte
    -1.73
    Ꮮ
    -1.72
    ꪔ
    -1.68
    ʬ
    -1.66
    POSITIVE LOGITS
     of
    2.91
    2
    2.42
    3
    2.14
    8
    2.00
    \
    1.98
    6
    1.79
    /
    1.65
     assures
    1.64
    又在
    1.63
    5
    1.63
    Act Density 0.026%

    No Known Activations