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

    Neuronpedia

    INDEX
    Explanations

    Removing parts of code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    INavigation
    -0.08
    \ActiveForm
    -0.07
    leitung
    -0.07
    㴔
    -0.07
     heats
    -0.07
    -0.06
     accompagn
    -0.06
    Provides
    -0.06
    -0.06
    Running
    -0.06
    POSITIVE LOGITS
    提出
    0.07
     أنا
    0.07
    寻求
    0.06
    уй
    0.06
    حق
    0.06
    槿
    0.06
    ไหว
    0.06
    但现在
    0.06
     sand
    0.06
    可用
    0.06
    Act Density 0.116%

    No Known Activations