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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     holiday
    -0.07
     wang
    -0.06
    Warnings
    -0.06
        
    -0.06
    	entity
    -0.06
    	back
    -0.06
    ()],
    -0.06
    ;&
    -0.06
    Responder
    -0.06
    oliday
    -0.06
    POSITIVE LOGITS
    qa
    0.07
    code
    0.07
    ός
    0.06
     empowering
    0.06
    _PROM
    0.06
    Bài
    0.06
    ิง
    0.06
     appeals
    0.06
     výše
    0.06
    онах
    0.06
    Act Density 0.009%

    No Known Activations