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

    Neuronpedia

    INDEX
    Explanations

    Future predictions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     warrant
    -0.07
     doing
    -0.06
    рование
    -0.06
     Those
    -0.06
    .usage
    -0.06
     „
    -0.06
     threat
    -0.06
     manner
    -0.06
     inflicted
    -0.06
     CERT
    -0.06
    POSITIVE LOGITS
     Coconut
    0.08
     Buckley
    0.08
    	queue
    0.07
    VA
    0.07
    ده
    0.07
    ोड
    0.07
     EntryPoint
    0.06
    argas
    0.06
     فارس
    0.06
     OSC
    0.06
    Act Density 0.016%

    No Known Activations