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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     :
↵
    -0.07
    <Type
    -0.06
    _multi
    -0.06
    Strange
    -0.06
     "}↵
    -0.06
    .schema
    -0.06
     prey
    -0.06
    _folder
    -0.06
     alb
    -0.06
    compressed
    -0.06
    POSITIVE LOGITS
     zvol
    0.07
     DIE
    0.06
     Hp
    0.06
    増
    0.06
     hashed
    0.06
     pthread
    0.06
    нуть
    0.06
     tý
    0.06
    해
    0.06
     сегодня
    0.06
    Act Density 0.136%

    No Known Activations