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

    Neuronpedia

    INDEX
    Explanations

    references to research studies and their findings

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

    introducing findings and reports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SPATH
    -0.53
     purpoſe
    -0.52
    RegistryLite
    -0.51
     '\\;'
    -0.50
     Houſe
    -0.50
     Ready
    -0.47
    ſelf
    -0.47
     Reſ
    -0.46
     Anſ
    -0.46
     pleaſure
    -0.45
    POSITIVE LOGITS
     désolés
    0.49
    posedge
    0.40
    AndEndTag
    0.40
    Diwedd
    0.36
    HasForeignKey
    0.36
     investigación
    0.35
     scientists
    0.35
     teorías
    0.35
     penelitian
    0.35
     bờ
    0.35
    Act Density 0.071%

    No Known Activations