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

    Neuronpedia

    INDEX
    Explanations

    methods related to getting and setting values in a coding context

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

    programming getters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     houſe
    -0.71
     itſelf
    -0.61
     raiſ
    -0.61
     ſta
    -0.57
     ſche
    -0.55
     tranſ
    -0.53
     pleaſure
    -0.52
    ſelves
    -0.51
     himſelf
    -0.50
     purpoſe
    -0.49
    POSITIVE LOGITS
    بوابة
    0.53
    RectangleBorder
    0.51
    EndProject
    0.49
     useCallback
    0.49
    Parcelize
    0.49
    хьтан
    0.48
     '{@
    0.48
    ấm
    0.45
     astore
    0.44
    rarr
    0.41
    Act Density 0.004%

    No Known Activations