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

    Neuronpedia

    INDEX
    Explanations

    patterns and structures in data, especially in relation to mathematical or statistical representations

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

    DSS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.90
    AndEndTag
    -0.82
     imagui
    -0.80
    ſicht
    -0.79
    niſſe
    -0.77
    <unused23>
    -0.75
    <unused42>
    -0.75
    <unused16>
    -0.75
    <pad>
    -0.75
    <unused8>
    -0.75
    POSITIVE LOGITS
    MathML
    0.29
     évit
    0.26
     armados
    0.24
     sayesinde
    0.24
    低
    0.24
    u
    0.24
     sør
    0.24
     Settlement
    0.23
     metá
    0.23
     ficando
    0.23
    Act Density 0.147%

    No Known Activations