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

    Neuronpedia

    INDEX
    Explanations

    Java syntax and structure in code snippets

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

    starts with user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     именно
    -0.29
    ESTRE
    -0.28
    LabelTagHelper
    -0.28
     segmento
    -0.28
     بق
    -0.28
    ILIA
    -0.28
    ofold
    -0.27
     em
    -0.27
    And
    -0.27
     yat
    -0.26
    POSITIVE LOGITS
    RTEX
    0.75
    SequentialGroup
    0.68
     насељу
    0.60
    ंदीखरीदारी
    0.59
    +:+
    0.59
     '\\;'
    0.54
    IVEREF
    0.52
    AntiForgeryToken
    0.52
    findpost
    0.50
     Ambiental
    0.50
    Act Density 0.006%

    No Known Activations