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

    Neuronpedia

    INDEX
    Explanations

    relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (level
    -0.07
     Testing
    -0.07
    ichert
    -0.06
     منتشر
    -0.06
    thead
    -0.06
    РСР
    -0.06
    ulo
    -0.06
    cth
    -0.06
     Dexter
    -0.06
     اخلاق
    -0.06
    POSITIVE LOGITS
    .ConnectionString
    0.07
    .ReLU
    0.06
     знач
    0.06
    Ngoài
    0.06
     grows
    0.06
    Club
    0.06
    pal
    0.06
    (signature
    0.06
    à
    0.06
    	Spring
    0.06
    Act Density 0.075%

    No Known Activations