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

    Neuronpedia

    INDEX
    Explanations

    Once

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ardware
    -0.06
    .enabled
    -0.06
    なが
    -0.06
    ESTAMP
    -0.06
    .createNew
    -0.06
     plethora
    -0.06
     Над
    -0.06
    amework
    -0.06
     basit
    -0.06
    	items
    -0.06
    POSITIVE LOGITS
    Once
    0.09
     Once
    0.08
    '";
↵
    0.07
     الق
    0.07
    '>".$
    0.07
     požad
    0.07
    axe
    0.07
     scrapped
    0.06
    -----↵↵
    0.06
    ort
    0.06
    Act Density 0.008%

    No Known Activations