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

    Neuronpedia

    INDEX
    Explanations

    w

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Space
    -0.07
    (r
    -0.07
    Side
    -0.07
    RP
    -0.06
    ๊ก
    -0.06
     cmd
    -0.06
     cruel
    -0.06
     있어
    -0.06
    	null
    -0.06
    
    -0.06
    POSITIVE LOGITS
    ควบค
    0.08
    wa
    0.07
     newfound
    0.07
    �
    0.07
     khó
    0.06
     plantation
    0.06
    324
    0.06
    bote
    0.06
    w
    0.06
     disbelief
    0.06
    Act Density 0.010%

    No Known Activations