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

    Neuronpedia

    INDEX
    Explanations

    requests for information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uins
    -0.08
    ROY
    -0.08
    Worst
    -0.08
    asaki
    -0.08
    ukkan
    -0.07
     подраз
    -0.07
     চাল
    -0.07
    adik
    -0.07
     cheeks
    -0.07
     আ
    -0.07
    POSITIVE LOGITS
    今
    0.10
    ぜひ
    0.10
    Interested
    0.09
     participating
    0.09
     interested
    0.09
    particip
    0.09
    参与
    0.09
     participation
    0.09
     takeaway
    0.09
     Teilnahme
    0.08
    Act Density 0.151%

    No Known Activations