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

    Neuronpedia

    INDEX
    Explanations

    text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     soll
    -0.07
    ลาด
    -0.07
     Pedro
    -0.07
    .jar
    -0.06
     Polly
    -0.06
    <p
    -0.06
     ignorant
    -0.06
     Charg
    -0.06
    빠
    -0.06
    \Exceptions
    -0.06
    POSITIVE LOGITS
     insanity
    0.07
    amientos
    0.07
    _life
    0.07
    (Arrays
    0.07
    055
    0.06
     Timestamp
    0.06
     stoi
    0.06
    col
    0.06
    starting
    0.06
    邮箱
    0.06
    Act Density 0.003%

    No Known Activations