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

    Neuronpedia

    INDEX
    Explanations

    quantities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cannes
    -0.06
     Scenes
    -0.06
    actual
    -0.06
    -results
    -0.06
    汇
    -0.06
     drag
    -0.06
     shipping
    -0.06
    lk
    -0.06
    ropa
    -0.06
     THESE
    -0.06
    POSITIVE LOGITS
    軽
    0.08
    찬
    0.07
     Loaded
    0.07
    pend
    0.06
    	sprite
    0.06
    čník
    0.06
    十四
    0.06
     Split
    0.06
    ).*
    0.06
     Aydın
    0.06
    Act Density 0.054%

    No Known Activations