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

    Neuronpedia

    INDEX
    Explanations

    contractions/possessives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    !“
    -0.07
     primal
    -0.06
     tình
    -0.06
    (zip
    -0.06
     betting
    -0.06
    ecs
    -0.06
    SW
    -0.06
    اصل
    -0.06
    世界
    -0.06
    rectangle
    -0.06
    POSITIVE LOGITS
    rightarrow
    0.06
     cope
    0.06
    eres
    0.06
     acre
    0.06
     Table
    0.06
     samot
    0.06
     UIB
    0.06
    [h
    0.06
     jednu
    0.06
    vání
    0.06
    Act Density 0.043%

    No Known Activations