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

    Neuronpedia

    INDEX
    Explanations

    a mix of emotions and experiences expressed through phrases

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

    Mixture of Chinese, Japanese, and English

    np_acts-logits-general · gemini-2.0-flash

    Chinese, Japanese, rivers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    utella
    -0.53
      
    -0.52
     most
    -0.50
    -
    -0.50
     
    -0.49
    <eos>
    -0.47
     nervous
    -0.47
     G
    -0.46
     -
    -0.45
    ˈ
    -0.44
    POSITIVE LOGITS
     ddelweddau
    0.85
     AppModule
    0.79
    Vidite
    0.77
     myſelf
    0.75
     Италијани
    0.75
    ]));
    0.74
    forRoot
    0.73
     plegable
    0.73
     Monfieur
    0.73
     تانيه
    0.72
    Act Density 0.062%

    No Known Activations