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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    another
    -0.08
    imetype
    -0.07
    템
    -0.07
    كز
    -0.07
     Pickup
    -0.07
    CY
    -0.07
     velké
    -0.07
    ?,
    -0.07
    ρου
    -0.07
     текст
    -0.07
    POSITIVE LOGITS
    _skb
    0.07
    kim
    0.06
    .walk
    0.06
     궁
    0.06
     القد
    0.06
    ปฏ
    0.06
     passphrase
    0.06
    _oauth
    0.06
    _BUF
    0.06
     transaction
    0.05
    Act Density 0.060%

    No Known Activations