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

    Neuronpedia

    INDEX
    Explanations

    testing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hizmet
    -0.08
     Strait
    -0.07
    ANNOT
    -0.07
     [{'
    -0.07
     pět
    -0.07
    	State
    -0.06
     поруш
    -0.06
     مردم
    -0.06
    qc
    -0.06
     safezone
    -0.06
    POSITIVE LOGITS
     BETWEEN
    0.07
     experimented
    0.07
     Getting
    0.07
    821
    0.06
     �
    0.06
    efd
    0.06
     conspiracy
    0.06
     ads
    0.06
    _due
    0.06
     lend
    0.06
    Act Density 0.001%

    No Known Activations