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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or changes

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

    "if you want", "If you're interested"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gro
    -0.40
     nakalista
    -0.38
    StructEnd
    -0.38
    Javadoc
    -0.37
     amen
    -0.37
     Wallace
    -0.36
    Портали
    -0.36
    Filmografia
    -0.36
     éve
    -0.36
     tail
    -0.36
    POSITIVE LOGITS
     NSCoder
    0.65
    tagHelperRunner
    0.55
    fjspx
    0.50
     allora
    0.48
     yoksa
    0.48
    PERATURE
    0.45
    出版年
    0.45
     utafitiHapana
    0.44
     zijne
    0.44
    convite
    0.44
    Act Density 0.024%

    No Known Activations