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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a method or process

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

    passing through, by, via

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cell
    -0.33
     Nuestros
    -0.33
    styleType
    -0.32
    UIControlState
    -0.32
     boils
    -0.31
    CELL
    -0.31
     случи
    -0.30
    l
    -0.30
    <bos>
    -0.30
     imageName
    -0.30
    POSITIVE LOGITS
    通过
    1.57
    通過
    1.46
     通过
    1.37
    透過
    1.09
    可以通过
    0.91
    透过
    0.84
     passing
    0.84
     통해
    0.84
     durch
    0.83
    through
    0.81
    Act Density 0.002%

    No Known Activations