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

    Neuronpedia

    INDEX
    Explanations

    specific movie titles or references

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

    Followed by prepositions or names

    np_acts-logits-general · gemini-2.0-flash

    popular films and characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ffilm
    -0.52
    PrototypeOf
    -0.52
    UnusedPrivate
    -0.50
    GenerationType
    -0.49
     fuori
    -0.44
    esm
    -0.44
    ​
    -0.43
    enschappelijke
    -0.43
     плат
    -0.43
    нале
    -0.42
    POSITIVE LOGITS
    ArrowToggle
    0.76
     Transformers
    0.73
    transformers
    0.71
     Pokémon
    0.68
     transformers
    0.68
     Pokemon
    0.65
     Naruto
    0.64
     Batman
    0.62
     Harry
    0.61
     Roskov
    0.61
    Act Density 0.217%

    No Known Activations