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

    Neuronpedia

    INDEX
    Explanations

    the letter 'H' and the underscore character

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

    hexadecimal code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.52
     femininas
    -0.46
     BrowserModule
    -0.44
     demás
    -0.43
    原始内容
    -0.40
     comunicarse
    -0.39
     tangki
    -0.39
     nacionais
    -0.38
     navideño
    -0.37
     cejas
    -0.37
    POSITIVE LOGITS
     ExecuteAsync
    0.56
     Paste
    0.55
     pasted
    0.51
    ölkerung
    0.50
    kable
    0.50
     Simpli
    0.49
     Dere
    0.48
    rettes
    0.47
    obis
    0.47
    ounces
    0.47
    Act Density 0.021%

    No Known Activations