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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bald
    -0.07
     Sid
    -0.06
    Sid
    -0.06
    Bind
    -0.06
     EVT
    -0.06
    .Marker
    -0.06
    .Note
    -0.06
    ihan
    -0.05
    bled
    -0.05
     halted
    -0.05
    POSITIVE LOGITS
    鲜
    0.07
     chính
    0.07
     Thought
    0.07
    俺は
    0.07
    이가
    0.06
    (metadata
    0.06
     Technologies
    0.06
    ourg
    0.06
    .clearRect
    0.06
    liche
    0.06
    Act Density 0.009%

    No Known Activations