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

    Neuronpedia

    INDEX
    Explanations

    First aid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dest
    -0.07
    TZ
    -0.06
     nick
    -0.06
    Simon
    -0.06
     сіль
    -0.06
     tiện
    -0.06
    vn
    -0.06
    nst
    -0.06
    animal
    -0.06
    収
    -0.06
    POSITIVE LOGITS
     يكون
    0.07
     ilişk
    0.07
     superclass
    0.07
    ><![
    0.07
     (![
    0.06
    .inflate
    0.06
    	console
    0.06
    朋
    0.06
     aalborg
    0.06
     أكبر
    0.06
    Act Density 0.005%

    No Known Activations