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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	direction
    -0.06
     expose
    -0.06
    onth
    -0.06
     circulated
    -0.06
    koli
    -0.06
     خواست
    -0.06
     exposed
    -0.06
     lời
    -0.06
     sunny
    -0.06
     gå
    -0.06
    POSITIVE LOGITS
     віт
    0.07
     hijos
    0.06
    (meta
    0.06
    轻
    0.06
    ケット
    0.06
     bearings
    0.06
    档
    0.06
    mps
    0.06
    ]<<"
    0.06
     October
    0.06
    Act Density 0.000%

    No Known Activations