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

    Neuronpedia

    INDEX
    Explanations

    terms related to ponies and horse-related themes

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

    Pony GT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "");
    -0.47
     viscose
    -0.45
    ‗
    -0.42
    森
    -0.41
     Lucie
    -0.39
     суда
    -0.39
     ")";
    -0.38
    Secrets
    -0.38
    '");
    -0.38
    "")
    -0.38
    POSITIVE LOGITS
    Pony
    0.95
     Pony
    0.95
     pony
    0.94
     ponies
    0.86
    pony
    0.78
    gasus
    0.76
     caballos
    0.73
     Stallion
    0.72
    Mustang
    0.71
    intenant
    0.69
    Act Density 0.014%

    No Known Activations