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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     económ
    -0.07
    kých
    -0.06
    。この
    -0.06
    	animation
    -0.06
     Judgment
    -0.06
    $f
    -0.06
    itorio
    -0.06
     Driving
    -0.06
    ↵↵↵↵↵↵↵
    -0.06
    morph
    -0.06
    POSITIVE LOGITS
     SID
    0.07
    ]++;↵
    0.06
     стари
    0.06
     близ
    0.06
     ман
    0.06
     barren
    0.06
    .Reverse
    0.06
    扎
    0.06
     decis
    0.06
    顶
    0.06
    Act Density 0.001%

    No Known Activations