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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "hit," including terms related to striking or being struck

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

    verbs and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.42
    IMPORTED
    -0.42
     keten
    -0.40
    ┛
    -0.40
    IntoConstraints
    -0.40
     inflater
    -0.37
     noqa
    -0.37
    antMatchers
    -0.36
     incendie
    -0.36
    LEncoder
    -0.36
    POSITIVE LOGITS
    endpush
    0.45
    didSet
    0.44
    writeField
    0.43
    SequentialGroup
    0.42
     onPostExecute
    0.41
    sofá
    0.40
    ništ
    0.40
     kjø
    0.40
     ragaz
    0.40
    хіво
    0.40
    Act Density 0.060%

    No Known Activations