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

    Neuronpedia

    INDEX
    Explanations

    unclear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .toast
    -0.08
    ”（
    -0.08
     beispielsweise
    -0.08
    》（
    -0.08
     ટ્ર
    -0.08
     zab
    -0.07
     esimerkiksi
    -0.07
     vink
    -0.07
     }:
    -0.07
     specialising
    -0.07
    POSITIVE LOGITS
     mysteries
    0.11
     perplex
    0.09
     misterio
    0.09
    无法
    0.09
     unclear
    0.08
     Quite
    0.08
     satisfactory
    0.08
    .Unknown
    0.08
     Mystery
    0.08
     mystery
    0.08
    Act Density 0.045%

    No Known Activations