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

    Neuronpedia

    INDEX
    Explanations

    concepts related to physical objects or systems

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

    preceding adjectives

    np_acts-logits-general · gemini-2.0-flash

    human/humain in different languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ագրություններ
    -0.54
     صوتيه
    -0.52
     الرياضيه
    -0.51
     ligiloj
    -0.50
     Biôgrafia
    -0.49
     CreateTagHelper
    -0.47
    spotted
    -0.47
     Scrub
    -0.46
     يتيمه
    -0.46
    ंदीखरीदारी
    -0.46
    POSITIVE LOGITS
     humains
    0.49
    osoba
    0.46
     humaines
    0.43
     humanas
    0.39
     manusia
    0.39
     ſte
    0.39
     humain
    0.38
     anſ
    0.38
     menschlichen
    0.38
     vaz
    0.38
    Act Density 0.981%

    No Known Activations