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

    Neuronpedia

    INDEX
    Explanations

    =(

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     classical
    -0.07
     explorer
    -0.07
    ＞
    -0.07
     };
    -0.07
     Indones
    -0.06
    ...)↵
    -0.06
    aversal
    -0.06
     safeguards
    -0.06
    (IO
    -0.06
     Ко
    -0.06
    POSITIVE LOGITS
     GRAT
    0.07
    ENTIC
    0.06
    .Patient
    0.06
    icit
    0.06
    ahir
    0.06
    .AnchorStyles
    0.06
    =(
    0.06
    ۱۵
    0.06
    icrosoft
    0.06
    	spec
    0.06
    Act Density 0.001%

    No Known Activations