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

    Neuronpedia

    INDEX
    Explanations

    phrases that express innovation or new approaches to problems

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

    new way outlook approach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.65
     ComVisible
    -0.58
    Obrázky
    -0.55
    BufferException
    -0.53
     navideños
    -0.52
    saraba
    -0.51
    󠁬
    -0.50
     daß
    -0.48
    -------------</
    -0.47
     wireType
    -0.47
    POSITIVE LOGITS
     Renewed
    0.50
    renewal
    0.50
    renew
    0.50
     renewed
    0.47
     rejuvenation
    0.47
     Renewal
    0.46
     renewal
    0.46
     Another
    0.44
     rebirth
    0.44
     reformation
    0.44
    Act Density 0.040%

    No Known Activations