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

    Neuronpedia

    INDEX
    Explanations

    Experts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amina
    -0.07
    ruise
    -0.07
    ænd
    -0.06
    Inserted
    -0.06
     ethnic
    -0.06
    리지
    -0.06
    -0.06
     Dry
    -0.06
     filthy
    -0.06
    town
    -0.06
    POSITIVE LOGITS
     inviting
    0.07
     leggings
    0.06
    らしい
    0.06
     دف
    0.06
    atabases
    0.06
    /reg
    0.06
    险
    0.06
    _semaphore
    0.06
    /we
    0.06
     Svens
    0.06
    Act Density 0.007%

    No Known Activations