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

    Neuronpedia

    INDEX
    Explanations

    bring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unpleasant
    -0.07
    nement
    -0.07
    IMARY
    -0.07
    和
    -0.07
    تق
    -0.06
     прис
    -0.06
    aka
    -0.06
     넘
    -0.06
    تری
    -0.06
    NX
    -0.06
    POSITIVE LOGITS
     htmlFor
    0.06
     Longer
    0.06
     Conv
    0.06
    SSF
    0.06
    Fr
    0.06
     Cambridge
    0.06
    -highlight
    0.06
    	Double
    0.06
    urrence
    0.05
     karar
    0.05
    Act Density 0.013%

    No Known Activations