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

    Neuronpedia

    INDEX
    Explanations

    century

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    thenReturn
    -0.07
    میل
    -0.06
     summers
    -0.06
    Jimmy
    -0.06
     learn
    -0.06
    	player
    -0.06
     doğrudan
    -0.06
    四
    -0.06
    PP
    -0.06
    ISODE
    -0.06
    POSITIVE LOGITS
    rı
    0.07
     lọc
    0.07
     newfound
    0.07
     dafür
    0.06
    unate
    0.06
    促
    0.06
     Miz
    0.06
    (coord
    0.06
     Expansion
    0.06
    세대
    0.06
    Act Density 0.002%

    No Known Activations