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

    Neuronpedia

    INDEX
    Explanations

    expressions and discussions surrounding personal beliefs and societal expectations

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

    should followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.84
    BufferException
    -0.72
    majánló
    -0.70
     Weiſe
    -0.70
    出版年
    -0.69
     Infórmanos
    -0.69
    <unused23>
    -0.69
    <unused16>
    -0.69
    [@BOS@]
    -0.69
    <unused28>
    -0.68
    POSITIVE LOGITS
     person
    0.37
     total
    0.35
     Pan
    0.34
     envol
    0.33
    ,
    0.33
     pan
    0.33
     balance
    0.32
     le
    0.32
     en
    0.32
     Auf
    0.32
    Act Density 0.140%

    No Known Activations