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

    Neuronpedia

    INDEX
    Explanations

    dimensions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    raq
    -0.08
     relevant
    -0.07
     teş
    -0.07
    _exit
    -0.07
     Kl
    -0.06
    -my
    -0.06
    Fake
    -0.06
     striving
    -0.06
    statement
    -0.06
    Secondary
    -0.06
    POSITIVE LOGITS
    SHOT
    0.06
     vortex
    0.06
    .getWidth
    0.06
     paperwork
    0.06
        
↵    
↵
    0.06
     reun
    0.06
     }

↵
    0.06
    قع
    0.06
    credible
    0.06
     lawful
    0.06
    Act Density 0.004%

    No Known Activations