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

    Neuronpedia

    INDEX
    Explanations

    problems and solutions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    开发
    -0.08
     cond
    -0.07
    Creation
    -0.07
    Reco
    -0.07
     acquired
    -0.07
    Acquire
    -0.07
     či
    -0.07
    开展
    -0.07
     frecuencia
    -0.07
    Ge
    -0.07
    POSITIVE LOGITS
    救世
    0.09
     Salvation
    0.08
     punitive
    0.08
     الحساب
    0.08
    halte
    0.08
     salvation
    0.08
     Parlament
    0.08
     presumed
    0.08
    valg
    0.08
     Ј
    0.08
    Act Density 0.000%

    No Known Activations