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

    Neuronpedia

    INDEX
    Explanations

    ubl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    弊
    -0.08
    afs
    -0.08
    vict
    -0.08
    侵
    -0.07
    博士
    -0.07
    さ
    -0.07
     Martina
    -0.07
     Aman
    -0.07
    紀
    -0.07
    でしょう
    -0.07
    POSITIVE LOGITS
     lam
    0.07
     Jeremy
    0.07
     '\
    0.07
    Firm
    0.07
    ಬ್ಬ
    0.07
     sheen
    0.07
    reas
    0.07
     giant
    0.07
     DSM
    0.07
    _Z
    0.07
    Act Density 0.001%

    No Known Activations