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

    Neuronpedia

    INDEX
    Explanations

    branch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     impulse
    -0.07
    ayd
    -0.07
     safest
    -0.06
    emet
    -0.06
     Truman
    -0.06
    Correct
    -0.06
    зм
    -0.06
    ์ช
    -0.06
    (Dictionary
    -0.06
    akte
    -0.06
    POSITIVE LOGITS
     premiere
    0.07
     Variable
    0.07
     Study
    0.07
    /questions
    0.07
     Repo
    0.06
    cin
    0.06
     Exists
    0.06
    ,Th
    0.06
     آهنگ
    0.06
     Ranger
    0.06
    Act Density 0.000%

    No Known Activations