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

    Neuronpedia

    INDEX
    Explanations

    .util

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '"+
    -0.07
     segunda
    -0.06
     Cloud
    -0.06
     Capac
    -0.06
     aes
    -0.06
    erta
    -0.06
    гот
    -0.06
    Community
    -0.05
     carg
    -0.05
    enga
    -0.05
    POSITIVE LOGITS
    است
    0.07
     RouterModule
    0.07
    .util
    0.07
     vụ
    0.07
    영
    0.06
    (userData
    0.06
     outspoken
    0.06
    (mut
    0.06
     slav
    0.06
    uso
    0.06
    Act Density 0.003%

    No Known Activations