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

    Neuronpedia

    INDEX
    Explanations

    occurrences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Е
    -0.07
     Моск
    -0.07
    ankind
    -0.07
    oran
    -0.07
    扫码
    -0.07
     Müslü
    -0.06
    ☷
    -0.06
     الإلك
    -0.06
     לצפ
    -0.06
    💺
    -0.06
    POSITIVE LOGITS
    xxxx
    0.07
    graph
    0.07
     boats
    0.07
    (Un
    0.07
    짓
    0.07
    _hard
    0.06
    	un
    0.06
    从未
    0.06
     psychiatric
    0.06
    _high
    0.06
    Act Density 0.017%

    No Known Activations