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

    Neuronpedia

    INDEX
    Explanations

    instances of instructions or guidance directed towards someone

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

    explaining to someone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Photocase
    -0.55
     Chwiliwch
    -0.54
    __*/
    -0.53
     combinations
    -0.52
    httphttps
    -0.51
     ProductService
    -0.51
     combination
    -0.50
     ActionResult
    -0.49
    postIndex
    -0.47
    escudo
    -0.47
    POSITIVE LOGITS
     inform
    0.42
     told
    0.42
     us
    0.42
     kepada
    0.41
     ComVisible
    0.40
     tell
    0.40
     envers
    0.39
    told
    0.39
    Told
    0.37
     Told
    0.37
    Act Density 0.019%

    No Known Activations