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

    Neuronpedia

    INDEX
    Explanations

    recounts of dining scenarios, including restaurant visits and meal descriptions.

    oai_token-act-pair · gemini-2.0-flash

    food appetite

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -1.13
     Efq
    -1.13
     ་་
    -1.11
     myſelf
    -1.09
     виправивши
    -1.05
    RUnlock
    -1.05
    存于互联网档案馆
    -1.02
     doubtnut
    -1.01
     Shakspeare
    -1.01
     Monfieur
    -0.99
    POSITIVE LOGITS
     
    0.49
    .
    0.45
     D
    0.43
    <eos>
    0.42
    ↵↵
    0.42
     e
    0.42
     is
    0.41
    di
    0.41
     y
    0.40
    :
    0.40
    Act Density 13.169%

    No Known Activations