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

    Neuronpedia

    INDEX
    Explanations

    repeated references to a "phone book" and "tika"

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

    java code or script

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.44
    Хьажоргаш
    -0.43
    numerusform
    -0.42
     desto
    -0.38
    principalColumn
    -0.38
    rrggbb
    -0.36
    TemporalType
    -0.36
    selas
    -0.36
     manners
    -0.35
    stare
    -0.35
    POSITIVE LOGITS
    Aholisi
    0.54
    rawDesc
    0.53
     betweenstory
    0.48
    /**
    0.47
    utilisons
    0.47
     виправивши
    0.42
    ########.
    0.41
     noDo
    0.41
     informée
    0.41
    bootstrapcdn
    0.40
    Act Density 0.004%

    No Known Activations