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

    Neuronpedia

    INDEX
    Explanations

    cash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     explain
    -0.07
    命
    -0.07
     genoemde
    -0.07
     hopeful
    -0.07
     ensure
    -0.07
    区
    -0.07
     unnecessary
    -0.07
     request
    -0.07
    详情
    -0.07
    clar
    -0.06
    POSITIVE LOGITS
     Gutschein
    0.10
     Instead
    0.10
     대신
    0.10
     Alternatives
    0.10
     amafaranga
    0.10
    Instead
    0.10
     ֆինանս
    0.09
     stipend
    0.09
     деньги
    0.09
    Equivalent
    0.09
    Act Density 0.063%

    No Known Activations