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

    Neuronpedia

    INDEX
    Explanations

    phrases requesting or indicating the need for assistance or guidance

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

    hint or clue for information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fully
    -0.35
    /**
    -0.32
    ératures
    -0.32
     citoy
    -0.31
     légal
    -0.31
    zegor
    -0.30
     complete
    -0.30
    资格
    -0.30
     Vit
    -0.29
     bienes
    -0.29
    POSITIVE LOGITS
     hinting
    0.92
     hinted
    0.89
     hints
    0.89
     hint
    0.88
     незавершена
    0.75
     clues
    0.75
     Hints
    0.74
    RTGC
    0.73
    hint
    0.69
     clue
    0.69
    Act Density 0.093%

    No Known Activations