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

    Neuronpedia

    INDEX
    Explanations

    phrases related to equality or similarity

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

    ".same(proto:" in code

    np_acts-logits-general · gemini-2.0-flash

    sameDomain, same way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resor
    -0.49
    ouille
    -0.47
    ualmente
    -0.46
     retired
    -0.46
     ſind
    -0.46
    الإنجليزية
    -0.46
    ivers
    -0.45
    iprot
    -0.44
     iprot
    -0.44
     parachute
    -0.44
    POSITIVE LOGITS
    تقاوى
    0.42
    httphttps
    0.38
    SAME
    0.36
    Дереккөздер
    0.36
     armonía
    0.35
     linkovi
    0.35
     Réponses
    0.35
     stijl
    0.35
     estético
    0.35
    årige
    0.34
    Act Density 0.029%

    No Known Activations