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

    Neuronpedia

    INDEX
    Explanations

    Italian text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     following
    -0.07
     adjusting
    -0.07
     Detection
    -0.06
     managers
    -0.06
    wendung
    -0.06
     Something
    -0.06
    Pro
    -0.06
     clipped
    -0.06
     같
    -0.06
     attention
    -0.06
    POSITIVE LOGITS
     rodi
    0.08
     deltaY
    0.07
    .StatusCode
    0.06
    	ST
    0.06
    ('');↵↵
    0.06
     grop
    0.06
    /NĐ
    0.06
    .netbeans
    0.06
    ([]);↵↵
    0.06
     miles
    0.06
    Act Density 0.011%

    No Known Activations