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
     нас
    -0.07
    せ
    -0.06
    _agents
    -0.06
    Chat
    -0.06
     signin
    -0.06
     HPV
    -0.06
    ้ก
    -0.06
    _project
    -0.06
     rg
    -0.06
    іна
    -0.06
    POSITIVE LOGITS
    testing
    0.07
    @interface
    0.07
    .shift
    0.07
     böl
    0.06
    groundColor
    0.06
    áz
    0.06
     Gott
    0.06
     Dumbledore
    0.06
     resid
    0.06
    帶
    0.06
    Act Density 0.006%

    No Known Activations