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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their contextual significance in discussions

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

    Fifth Avenue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     otomatig
    -0.88
    rungsseite
    -0.84
    <unused16>
    -0.79
    <unused8>
    -0.79
    <unused43>
    -0.79
    <unused41>
    -0.79
    <unused68>
    -0.79
    <unused74>
    -0.79
    <unused3>
    -0.79
    <unused14>
    -0.79
    POSITIVE LOGITS
    Bob
    0.33
    Next
    0.32
     Bob
    0.31
     
    0.30
    M
    0.29
    K
    0.29
    U
    0.29
    obj
    0.28
    OL
    0.28
    Line
    0.28
    Act Density 0.060%

    No Known Activations