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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     STAR
    -0.07
    dG
    -0.06
    	↵	↵	↵
    -0.06
    ↵↵↵↵↵↵↵↵↵↵↵
    -0.06
    Built
    -0.06
     �
    -0.06
    pts
    -0.06
     万
    -0.06
    گر
    -0.06
     Alejandro
    -0.06
    POSITIVE LOGITS
     residual
    0.08
    ीन
    0.07
    ertainment
    0.07
     Subscribe
    0.07
    .roll
    0.06
     quitting
    0.06
     molding
    0.06
     rubbed
    0.06
    Financial
    0.06
    business
    0.06
    Act Density 0.689%

    No Known Activations