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

    Neuronpedia

    INDEX
    Explanations

    /*

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     promptly
    -0.07
     [--
    -0.07
    镇政府
    -0.07
     באתר
    -0.07
     לקראת
    -0.07
     magg
    -0.07
    晚报
    -0.07
     componentWill
    -0.07
     bunny
    -0.07
     Attribute
    -0.06
    POSITIVE LOGITS
     fres
    0.08
     natural
    0.07
     simplified
    0.07
    乘
    0.07
    创
    0.07
     interrupt
    0.06
     balance
    0.06
    _available
    0.06
     dedic
    0.06
    ernet
    0.06
    Act Density 0.005%

    No Known Activations