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

    Neuronpedia

    INDEX
    Explanations

    file paths and directories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     হইয়াছিল
    0.86
    reset
    0.84
     bookkeeping
    0.78
     あっ
    0.78
    ordon
    0.77
    ኰ
    0.75
    Máy
    0.75
     ബു
    0.74
    localtime
    0.74
    history
    0.74
    POSITIVE LOGITS
    র্থ
    0.71
    年底
    0.69
     डिज
    0.65
    +'
    0.63
    брав
    0.62
    ध्य
    0.59
     encouraged
    0.59
    ="
    0.58
    来
    0.58
     championed
    0.58
    Act Density 0.131%

    No Known Activations