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

    Neuronpedia

    INDEX
    Explanations

    xt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    昃
    -0.08
     pkt
    -0.07
     serta
    -0.07
    	restore
    -0.07
    礁
    -0.07
    츠
    -0.07
    ält
    -0.07
     través
    -0.07
     wś
    -0.06
    เพชร
    -0.06
    POSITIVE LOGITS
     חייב
    0.07
    [_
    0.07
    筛选
    0.07
     Plans
    0.06
     Adrian
    0.06
    aload
    0.06
     Duch
    0.06
     critic
    0.06
    anny
    0.06
     שוב
    0.06
    Act Density 0.528%

    No Known Activations