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

    Neuronpedia

    INDEX
    Explanations

    single

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recomm
    -0.08
    ໄ
    -0.07
    _Date
    -0.07
    仪
    -0.07
    �
    -0.07
    ⛧
    -0.07
     водо
    -0.07
     navCtrl
    -0.07
    紧凑
    -0.07
    -sama
    -0.07
    POSITIVE LOGITS
    ，↵↵
    0.07
     Brisbane
    0.07
    ),↵
    0.07
     (-
    0.07
     (/
    0.07
     sadly
    0.07
     Sun
    0.07
    социальн
    0.07
     ridiculous
    0.07
     SELF
    0.07
    Act Density 0.004%

    No Known Activations