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

    Neuronpedia

    INDEX
    Explanations

    policy and guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    根据
    0.42
     apricots
    0.38
    нуть
    0.37
    根據
    0.36
    ﺰ
    0.36
     根据
    0.36
     tego
    0.34
    代替
    0.33
    依据
    0.32
     vasta
    0.31
    POSITIVE LOGITS
     regarding
    0.53
     بشأن
    0.52
    regarding
    0.51
    established
    0.47
     dotycz
    0.46
     miserably
    0.46
    despite
    0.46
     वर्णित
    0.46
    requirements
    0.45
    adham
    0.44
    Act Density 0.016%

    No Known Activations