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

    Neuronpedia

    INDEX
    Explanations

    elements related to software components and their configurations

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

    insert user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     otomatig
    -0.93
    <unused41>
    -0.91
    <unused79>
    -0.91
    <unused23>
    -0.91
    <unused52>
    -0.91
    <unused68>
    -0.91
    <unused74>
    -0.91
    <unused42>
    -0.91
    <unused8>
    -0.91
    <unused16>
    -0.91
    POSITIVE LOGITS
    SuspendLayout
    0.44
     devoted
    0.26
     dedicated
    0.26
    <strong>
    0.25
    1
    0.25
     Division
    0.25
    2
    0.25
    ↵
    0.25
    ↵↵
    0.24
    Â
    0.23
    Act Density 0.000%

    No Known Activations