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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dışarı
    -0.06
     luxe
    -0.06
     nevid
    -0.06
     Κα
    -0.06
     nood
    -0.06
    onenumber
    -0.06
     součas
    -0.05
    
    -0.05
     ÜNİVERS
    -0.05
    .uml
    -0.05
    POSITIVE LOGITS
     Rebecca
    0.07
    becca
    0.07
     </>↵
    0.07
     vintage
    0.06
    ΙΤ
    0.06
     avoiding
    0.06
     laptop
    0.06
     spotting
    0.06
    ERA
    0.06
     crim
    0.06
    Act Density 0.000%

    No Known Activations