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

    Neuronpedia

    INDEX
    Explanations

    Period symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    レ
    -0.07
    (hidden
    -0.07
     Tide
    -0.07
    ۸
    -0.07
    _reservation
    -0.07
    -taking
    -0.07
    단
    -0.07
     повтор
    -0.06
    濃
    -0.06
     подум
    -0.06
    POSITIVE LOGITS
     scre
    0.07
    ชม
    0.06
    Allows
    0.06
    เทคโนโลย
    0.06
     прек
    0.06
    Comic
    0.06
     soruml
    0.06
     Grupo
    0.06
    pkt
    0.06
    	PORT
    0.05
    Act Density 0.001%

    No Known Activations