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

    Neuronpedia

    INDEX
    Explanations

    pronouns and personal references

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

    pronouns followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дописавши
    -0.84
    AndroidJUnit
    -0.71
    +#+#
    -0.57
    Diwedd
    -0.57
    WithIOException
    -0.54
    <bos>
    -0.54
     SwitchCompat
    -0.52
    encu
    -0.51
    UseVisualStyle
    -0.50
    WebServlet
    -0.50
    POSITIVE LOGITS
     أنها
    0.52
     ότι
    0.50
     bahawa
    0.43
     skall
    0.41
     πως
    0.40
     üzere
    0.40
     tersebut
    0.39
     kwamba
    0.39
     أنه
    0.38
    ="#">
    0.38
    Act Density 0.062%

    No Known Activations