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

    Neuronpedia

    INDEX
    Explanations

    specific website links or references

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

    chat usernames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Clik
    -0.63
    bootstrapcdn
    -0.52
    Hentet
    -0.47
    Controllo
    -0.47
     kasarigan
    -0.47
    WithMany
    -0.46
    Autoritní
    -0.45
    sre
    -0.44
     programme
    -0.43
    ndor
    -0.43
    POSITIVE LOGITS
     amizade
    0.51
    GOTREF
    0.44
     amitié
    0.42
     fermée
    0.38
     répondu
    0.38
     céramique
    0.37
     magnétique
    0.37
     oreille
    0.36
     légitime
    0.36
    EndGlobalSection
    0.35
    Act Density 0.020%

    No Known Activations