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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mui
    -0.07
    ams
    -0.07
    iz
    -0.07
     Cruc
    -0.07
    Employ
    -0.06
    艦
    -0.06
    ВС
    -0.06
    Paint
    -0.06
     crucial
    -0.06
    werk
    -0.06
    POSITIVE LOGITS
     (>
    0.07
    的一
    0.06
     grap
    0.06
     {:.
    0.06
     ACCEPT
    0.06
     понима
    0.06
     [#
    0.06
     vypad
    0.06
     dlou
    0.05
     theor
    0.05
    Act Density 0.045%

    No Known Activations