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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate reasoning, necessity, and potential outcomes

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

    wanting or needing to do something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mybatisplus
    -0.69
     linkovi
    -0.69
    SharedCtor
    -0.64
    twimg
    -0.59
    MLLoader
    -0.53
     desmotivaciones
    -0.52
    retudo
    -0.52
    bcryptjs
    -0.51
    Cyfarwyddwr
    -0.51
    istoitu
    -0.50
    POSITIVE LOGITS
     solution
    0.42
     ideas
    0.39
     form
    0.37
     jadx
    0.37
    solution
    0.37
     approach
    0.37
    wegs
    0.35
     order
    0.35
     static
    0.35
     plan
    0.35
    Act Density 0.039%

    No Known Activations