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

    Neuronpedia

    INDEX
    Explanations

    etched lines and weathered marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enveloped
    0.83
     veiled
    0.83
     contaminating
    0.81
     encased
    0.81
     curd
    0.80
     alloy
    0.77
     polluting
    0.76
     metallic
    0.76
     polymers
    0.76
     alloys
    0.75
    POSITIVE LOGITS
     scars
    1.00
     scratches
    0.94
     creases
    0.92
     marks
    0.91
     incurred
    0.84
    marks
    0.83
    Marks
    0.82
    わかる
    0.82
     segni
    0.80
     wrinkles
    0.79
    Act Density 0.072%

    No Known Activations