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

    Neuronpedia

    INDEX
    Explanations

    nil

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     casos
    -0.07
     Leia
    -0.07
    AuthGuard
    -0.06
    logradouro
    -0.06
     spouse
    -0.06
    ُه
    -0.06
    �
    -0.06
     ICU
    -0.06
     pitfalls
    -0.06
     justified
    -0.06
    POSITIVE LOGITS
    ¯
    0.06
    /'
    0.06
     للس
    0.06
     unb
    0.06
    polygon
    0.06
    ,eg
    0.06
     algorithms
    0.06
    -app
    0.06
    crate
    0.06
    .ApplyResources
    0.06
    Act Density 0.004%

    No Known Activations