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

    Neuronpedia

    INDEX
    Explanations

    coding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     standout
    -0.07
    享有
    -0.07
    /block
    -0.07
    COMMAND
    -0.07
     standings
    -0.07
    适用于
    -0.06
     Capability
    -0.06
     nome
    -0.06
     Man
    -0.06
    ちょ
    -0.06
    POSITIVE LOGITS
    –↵↵
    0.08
    的能量
    0.07
    كار
    0.07
                    ↵
    0.07
     lows
    0.07
    ↵    ↵    ↵
    0.06
     impres
    0.06
     engages
    0.06
    尪
    0.06
     хозяйств
    0.06
    Act Density 0.001%

    No Known Activations