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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     endorsement
    -0.07
    	list
    -0.07
    (annotation
    -0.06
     prevention
    -0.06
     Flood
    -0.06
     resolver
    -0.06
    бав
    -0.06
     "%
    -0.06
    .file
    -0.06
    ера
    -0.06
    POSITIVE LOGITS
    いに
    0.07
     nei
    0.07
     нали
    0.06
     ク
    0.06
     Alarm
    0.06
     thiên
    0.06
     зуп
    0.06
     imread
    0.06
     zdarma
    0.06
    .Config
    0.06
    Act Density 0.008%

    No Known Activations