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

    Neuronpedia

    INDEX
    Explanations

    commands related to removing elements from data structures

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

    removing items and polling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.57
     SIA
    -0.40
     estekak
    -0.39
     PSA
    -0.38
    esac
    -0.38
     ASI
    -0.37
    WEBPACK
    -0.36
    ''')
    -0.36
     RSSSF
    -0.36
     invokingState
    -0.35
    POSITIVE LOGITS
    remove
    0.84
     remove
    0.69
    expandindo
    0.58
    IntoConstraints
    0.58
     removing
    0.57
    removing
    0.56
    removal
    0.56
     REMOV
    0.56
    Remove
    0.56
     removal
    0.55
    Act Density 0.005%

    No Known Activations