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

    Neuronpedia

    INDEX
    Explanations

    saving python code files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Save
    0.46
     saver
    0.45
     example
    0.44
     Sava
    0.43
     indicator
    0.41
     saveData
    0.41
     PHP
    0.40
    managerpage
    0.40
     PYTHON
    0.40
     Sebastian
    0.40
    POSITIVE LOGITS
     credible
    0.39
    cream
    0.39
     playable
    0.38
    =
    0.38
    grav
    0.38
    גע
    0.38
    able
    0.37
    ken
    0.37
    outed
    0.37
    Suitable
    0.37
    Act Density 0.003%

    No Known Activations