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

    Neuronpedia

    INDEX
    Explanations

    references to political corruption and criminal activity

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

    Follows a title enclosed in quotation marks

    np_acts-logits-general · gemini-2.0-flash

    foreign names and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.63
     TextInputType
    -0.59
     Banach
    -0.52
     dataSnapshot
    -0.51
    classnames
    -0.51
     Schrödinger
    -0.51
     Scro
    -0.50
    obod
    -0.49
    +#+#
    -0.49
     aristocracy
    -0.49
    POSITIVE LOGITS
    AndEndTag
    0.58
    mink
    0.50
    comb
    0.50
     Poli
    0.50
    хьтан
    0.48
    Guar
    0.47
    kloped
    0.47
    sold
    0.46
    complexType
    0.46
    Armed
    0.46
    Act Density 0.053%

    No Known Activations