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

    Neuronpedia

    INDEX
    Explanations

    technical mathematical statements or terms related to proofs and theorems

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

    "If" statements within theorems or lemmas

    np_acts-logits-general · gemini-2.0-flash

    if condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LikeLiked
    -0.55
    engesch
    -0.53
     later
    -0.53
    <eos>
    -0.49
    atul
    -0.48
     ris
    -0.48
    ++;
    -0.48
     cuối
    -0.48
    LikeLike
    -0.48
     our
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.64
     demurrer
    0.63
    WebServlet
    0.63
    ✨:
    0.61
     Shakspeare
    0.60
     uLocal
    0.57
     rospy
    0.57
    GOTREF
    0.56
     للمعارف
    0.56
     AssemblyTitle
    0.56
    Act Density 1.119%

    No Known Activations