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

    Neuronpedia

    INDEX
    Explanations

    references to characters or elements from popular animated series

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

    pony characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    findpost
    -0.58
    MigrationBuilder
    -0.51
    AndEndTag
    -0.46
    SharedCtor
    -0.45
     olvides
    -0.44
    ])));
    -0.42
    RTEX
    -0.42
    ]}"
    -0.41
    ])]
    -0.40
     valentín
    -0.40
    POSITIVE LOGITS
    pony
    0.55
     Equest
    0.53
     Pony
    0.52
     ponies
    0.50
     pony
    0.49
    Pony
    0.48
    发表于
    0.45
     Pfer
    0.45
    Anhalt
    0.44
    Personendaten
    0.42
    Act Density 0.020%

    No Known Activations