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

    Neuronpedia

    INDEX
    Explanations

    references to right-click actions

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

    right direction or assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     McKinnon
    -0.98
    期刊论文
    -0.87
    __":
    -0.85
     Савезне
    -0.85
    Autoritní
    -0.84
     Scherer
    -0.84
    WireFormatLite
    -0.84
     Flanagan
    -0.83
     Cowan
    -0.81
    ectady
    -0.81
    POSITIVE LOGITS
    right
    0.91
    setRight
    0.90
     RIGHT
    0.81
    ght
    0.81
    RIGHT
    0.79
    wright
    0.78
    Right
    0.77
     Right
    0.77
     right
    0.75
     destra
    0.75
    Act Density 0.044%

    No Known Activations