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

    Neuronpedia

    INDEX
    Explanations

    scene descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abases
    0.80
     nightmares
    0.78
     sensibles
    0.77
     axons
    0.69
    ங்களைத்
    0.69
     Nerve
    0.68
     sensitivities
    0.68
     headaches
    0.67
     Termin
    0.67
    每次
    0.67
    POSITIVE LOGITS
     escena
    1.11
     scene
    1.10
     모습
    1.05
     smiling
    1.04
     장면
    1.01
    场景
    1.01
     scène
    1.01
     portrait
    1.00
     escenas
    0.99
     scena
    0.99
    Act Density 0.872%

    No Known Activations