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

    Neuronpedia

    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stral
    -0.27
    yps
    -0.26
     vez
    -0.26
    SystemService
    -0.26
     POR
    -0.26
     Cornwall
    -0.26
    increments
    -0.25
    ä¾Ŀ次
    -0.24
     einzel
    -0.24
     polo
    -0.24
    POSITIVE LOGITS
    .eu
    0.28
    apsible
    0.27
    createView
    0.26
     incons
    0.24
     Conc
    0.24
    ndef
    0.24
    çŁŃ线
    0.23
    ç²¾ç¥ŀ
    0.23
    çŁ¥åIJįä¼ģä¸ļ
    0.23
    æ°ijå±ħ
    0.23
    Act Density 0.264%

    No Known Activations