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

    Neuronpedia

    INDEX
    Explanations

    variations of the letter 's' in different forms and contexts

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

    user input prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.61
    Connection
    -0.45
    Ign
    -0.44
    toor
    -0.44
    PLAIN
    -0.44
    Gr
    -0.43
     Ign
    -0.42
    PTT
    -0.42
     Gottfried
    -0.42
     connection
    -0.42
    POSITIVE LOGITS
     са
    1.59
    Са
    1.00
    са
    0.90
     Са
    0.84
    Personendaten
    0.70
    ⟬
    0.66
     SafeArea
    0.61
    SequentialGroup
    0.61
     sat
    0.60
     nakalista
    0.59
    Act Density 0.001%

    No Known Activations