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

    Neuronpedia

    INDEX
    Explanations

    website data collection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mac
    -0.07
     Russian
    -0.06
     Mol
    -0.05
     learning
    -0.05
     UB
    -0.05
     cycle
    -0.05
     shedding
    -0.05
    dream
    -0.05
     Olympic
    -0.05
     incapable
    -0.05
    POSITIVE LOGITS
     několik
    0.08
     thousands
    0.07
    irit
    0.07
     lil
    0.07
     anymore
    0.07
    (await
    0.07
    ystatechange
    0.06
     ทำให
    0.06
     действ
    0.06
     nær
    0.06
    Act Density 0.017%

    No Known Activations