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

    Neuronpedia

    INDEX
    Explanations

    memories and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     borderRadius
    0.40
     powdered
    0.39
     भव्य
    0.39
     drap
    0.39
     intravenous
    0.38
     gallant
    0.38
     pulver
    0.38
     nebula
    0.36
     cardiovascular
    0.36
     capucha
    0.36
    POSITIVE LOGITS
    Meta
    0.50
    지에
    0.47
    存在
    0.47
     теорети
    0.46
    我不
    0.46
    地の
    0.45
    욬
    0.45
    지와
    0.45
    Une
    0.45
    지를
    0.44
    Act Density 0.016%

    No Known Activations