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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $_
    -0.09
     folklore
    -0.08
     effort
    -0.08
     infinit
    -0.08
    backend
    -0.07
    டுக்க
    -0.07
     dripping
    -0.07
    .backend
    -0.07
     watershed
    -0.07
     Cic
    -0.07
    POSITIVE LOGITS
    提醒
    0.09
    ton
    0.08
     Confeder
    0.08
     высокого
    0.08
     hopefully
    0.08
     Exhibition
    0.07
     fid
    0.07
    公布
    0.07
     ಬರುತ್ತ
    0.07
    公告
    0.07
    Act Density 0.011%

    No Known Activations