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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms associated with compiler warnings and diagnostics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    restoring state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -1.05
     betweenstory
    -0.80
    thâu
    -0.69
    دانشنامهٔ
    -0.67
     Chwiliwch
    -0.67
    ⓧ
    -0.66
     utafitiHapana
    -0.66
     الحره
    -0.65
    RegressionTest
    -0.64
    ſelves
    -0.63
    POSITIVE LOGITS
     restore
    0.57
     restored
    0.55
     restores
    0.51
    restore
    0.50
     restoration
    0.45
     restoring
    0.43
     Restore
    0.39
     Restoration
    0.39
    Restore
    0.39
     recovery
    0.37
    Act Density 0.001%

    No Known Activations