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

    Neuronpedia

    INDEX
    Explanations

    git diff and code review

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Implement
    0.38
    Initialization
    0.37
     Pinn
    0.37
     빈
    0.37
     corred
    0.36
    mvnrepository
    0.36
    Miss
    0.36
    笏
    0.36
    ician
    0.35
     Uninstall
    0.35
    POSITIVE LOGITS
     diff
    0.86
    diff
    0.80
     Diff
    0.77
     DIFF
    0.76
    Diff
    0.74
     patch
    0.74
     reviewers
    0.71
    patch
    0.71
    DIFF
    0.70
     Patch
    0.69
    Act Density 0.018%

    No Known Activations