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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    obr
    -0.08
     downfall
    -0.08
    ährungs
    -0.07
    (V
    -0.07
    Hari
    -0.07
     shepherd
    -0.07
    (fe
    -0.07
     можем
    -0.07
     grim
    -0.07
    (resp
    -0.07
    POSITIVE LOGITS
     printers
    0.08
     ED
    0.07
     വ്യാപ
    0.07
    Printed
    0.07
    TARGET
    0.07
     Ed
    0.07
     Preferred
    0.07
    Popular
    0.07
    Preferred
    0.07
     ವ್ಯಾಪ
    0.07
    Act Density 0.002%

    No Known Activations