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

    Neuronpedia

    INDEX
    Explanations

    technical terms and code references

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

    Code-related tokens or code snippets

    np_acts-logits-general · gemini-2.0-flash

    programming language keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ancla
    -0.24
     mêmes
    -0.23
     mañana
    -0.22
     présent
    -0.21
     chacune
    -0.20
     communautés
    -0.20
    ęki
    -0.19
     couverte
    -0.19
     gleichen
    -0.19
     Landschaft
    -0.19
    POSITIVE LOGITS
    <unused43>
    1.06
    <unused42>
    1.06
    <unused28>
    1.06
    <unused41>
    1.06
    <unused3>
    1.06
    [@BOS@]
    1.06
    <unused14>
    1.06
    <unused23>
    1.06
    <unused68>
    1.06
    <unused79>
    1.06
    Act Density 0.806%

    No Known Activations