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

    Neuronpedia

    INDEX
    Explanations

    geographical locations or affiliation

    oai_token-act-pair · gemini-2.0-flash

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     help
    -0.50
    <bos>
    -0.45
    portál
    -0.43
    THREADS
    -0.40
    あとは
    -0.40
    號
    -0.39
    <eos>
    -0.39
    enschappelijke
    -0.39
     he
    -0.39
     He
    -0.38
    POSITIVE LOGITS
     houſe
    0.80
     Theſe
    0.79
     Majefty
    0.71
     Monfieur
    0.71
     صوتيه
    0.71
     purpoſe
    0.69
     Houſe
    0.69
     itſelf
    0.68
    blockList
    0.67
     pleaſure
    0.67
    Act Density 0.568%

    No Known Activations