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

    Neuronpedia

    INDEX
    Explanations

    software-related technical terms and code structure

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

    file includes and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused41>
    -0.85
    <unused17>
    -0.85
    <unused51>
    -0.85
    <unused14>
    -0.85
    <unused32>
    -0.85
    [@BOS@]
    -0.85
    <unused68>
    -0.85
    <unused16>
    -0.85
    <unused8>
    -0.85
    <unused1>
    -0.85
    POSITIVE LOGITS
    Referanser
    0.32
     génie
    0.28
     tourisme
    0.24
     eius
    0.23
    Données
    0.22
    
    0.22
     règne
    0.22
     culturel
    0.22
     escalier
    0.21
     perí
    0.21
    Act Density 0.013%

    No Known Activations