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

    Neuronpedia

    INDEX
    Explanations

    Time values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     efficiency
    -0.07
    Ô
    -0.07
    χο
    -0.06
    混
    -0.06
    Clusters
    -0.06
    Tok
    -0.06
    sip
    -0.06
     тощо
    -0.06
    Internet
    -0.06
    UZ
    -0.06
    POSITIVE LOGITS
    ..↵
    0.07
    agogue
    0.07
     sildenafil
    0.07
    resolve
    0.06
     eup
    0.06
     Faker
    0.06
    ="<
    0.06
    ---------↵
    0.06
     :↵↵↵↵
    0.06
    ्ट
    0.06
    Act Density 0.009%

    No Known Activations