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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LAS
    -0.06
     kvm
    -0.06
     podstat
    -0.06
     arcs
    -0.06
     مرات
    -0.06
     panc
    -0.06
     kính
    -0.06
     vil
    -0.06
    Kel
    -0.06
     smoked
    -0.06
    POSITIVE LOGITS
     Documentation
    0.07
    olerance
    0.07
     Deliver
    0.07
     BYTE
    0.06
    uellement
    0.06
    оратив
    0.06
     Ramsey
    0.06
     Paperback
    0.06
    Manufacturer
    0.06
     occupy
    0.06
    Act Density 0.001%

    No Known Activations