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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     level
    -0.07
     	↵
    -0.06
     принцип
    -0.06
    們
    -0.06
    _an
    -0.06
     وش
    -0.06
    /re
    -0.06
    (speed
    -0.06
     Comparable
    -0.06
     chars
    -0.06
    POSITIVE LOGITS
     almak
    0.07
     earliest
    0.07
     England
    0.07
    izophren
    0.06
     Marcos
    0.06
     Patricia
    0.06
     SOCIAL
    0.06
     retired
    0.06
    Cro
    0.06
    -bottom
    0.06
    Act Density 0.008%

    No Known Activations