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

    Neuronpedia

    INDEX
    Explanations

    website content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kar
    -0.07
     Updating
    -0.07
    -bel
    -0.06
    jal
    -0.06
     EXT
    -0.06
    illary
    -0.06
    анси
    -0.06
    звичай
    -0.06
     charset
    -0.06
    import
    -0.06
    POSITIVE LOGITS
    '];
↵
↵
    0.07
     aute
    0.07
    олева
    0.06
    hibit
    0.06
     tarihi
    0.06
     wooded
    0.06
    iday
    0.06
    .Block
    0.06
    ُس
    0.06
     //
↵
↵
    0.06
    Act Density 0.007%

    No Known Activations