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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    瘐
    -0.07
    넷
    -0.07
     Stephens
    -0.07
    ᠄
    -0.07
    二季度
    -0.07
    百余
    -0.07
     создания
    -0.07
    -inc
    -0.07
    Ryan
    -0.07
    远景
    -0.07
    POSITIVE LOGITS
    post
    0.07
    -room
    0.07
    -full
    0.07
     argv
    0.07
     natural
    0.07
    .sub
    0.07
    .Form
    0.07
    -post
    0.07
    常
    0.06
    heat
    0.06
    Act Density 0.001%

    No Known Activations