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

    Neuronpedia

    INDEX
    Explanations

    software testing modules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    श्मीर
    1.68
     Vestone
    1.52
    ফট
    1.51
    どう
    1.48
     पूरे
    1.47
    п
    1.43
    蓉
    1.42
     hago
    1.41
    চিত
    1.40
    亼
    1.38
    POSITIVE LOGITS
     easements
    2.03
    ことです
    2.00
    芏
    1.99
    斻
    1.91
     autocorrelation
    1.87
     affinity
    1.84
     halting
    1.83
     onPressed
    1.83
     peptid
    1.73
     reverts
    1.72
    Act Density 0.000%

    No Known Activations