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

    Neuronpedia

    INDEX
    Explanations

    min

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     VH
    -0.06
     Peygamber
    -0.06
    972
    -0.06
    ेटर
    -0.06
     ย
    -0.06
    @\
    -0.06
    。。
    -0.05
     QFont
    -0.05
    ****↵
    -0.05
    OW
    -0.05
    POSITIVE LOGITS
     employing
    0.07
    .dispatcher
    0.07
    )paren
    0.07
    .common
    0.06
     tim
    0.06
     amend
    0.06
    시는
    0.06
     nhớ
    0.06
    	im
    0.06
    /settings
    0.06
    Act Density 0.006%

    No Known Activations