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

    Neuronpedia

    INDEX
    Explanations

    parts of sentences that discuss exceptions or contrasting ideas

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

    "> ... actually"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fullname
    -0.31
    Primary
    -0.31
    Replicas
    -0.31
    primary
    -0.30
     принадле
    -0.29
    eseorang
    -0.29
    Rotation
    -0.29
     Peters
    -0.28
     Rep
    -0.28
     Primary
    -0.28
    POSITIVE LOGITS
    elemField
    0.79
    principalColumn
    0.74
    +#+#
    0.71
    RenderAtEndOf
    0.66
    ModelSerializer
    0.66
    rungsseite
    0.65
     utafitiHapana
    0.63
    OGND
    0.63
    SequentialGroup
    0.62
     <<<<<<<<<<<<<<
    0.61
    Act Density 0.651%

    No Known Activations