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

    Neuronpedia

    INDEX
    Explanations

    references to Disney characters or attractions

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

    Follows "and," mathematical symbols, or numbers

    np_acts-logits-general · gemini-2.0-flash

    algebra setting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     industriels
    -0.51
     Nieto
    -0.50
     Setter
    -0.50
    Slab
    -0.49
     bandeja
    -0.48
    Volvo
    -0.47
     Tomasz
    -0.46
     mitsubishi
    -0.46
     seks
    -0.46
     Serbian
    -0.46
    POSITIVE LOGITS
     Disney
    1.65
    Disney
    1.47
     disney
    1.33
     Walt
    1.29
    disney
    1.18
     Mickey
    1.15
     Disneyland
    1.14
    Walt
    1.13
     WALT
    1.02
     ディズニー
    0.98
    Act Density 0.045%

    No Known Activations