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

    Neuronpedia

    INDEX
    Explanations

    year

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    자를
    -0.06
     Walters
    -0.06
     choses
    -0.05
     JSGlobal
    -0.05
     elf
    -0.05
    aversal
    -0.05
    xs
    -0.05
     tut
    -0.05
     Obs
    -0.05
    ForEach
    -0.05
    POSITIVE LOGITS
    nímu
    0.08
    月
    0.08
     started
    0.07
    同時
    0.07
     her
    0.07
     strands
    0.07
    rgba
    0.07
     skin
    0.07
     जल
    0.07
    .argv
    0.06
    Act Density 0.011%

    No Known Activations