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

    Neuronpedia

    INDEX
    Explanations

    predominantly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
     Liên
    -0.07
    借
    -0.07
    IJ
    -0.07
     להעביר
    -0.07
    妒
    -0.07
    �
    -0.07
     punched
    -0.07
    周三
    -0.07
     Dess
    -0.07
    POSITIVE LOGITS
    𬬹
    0.07
    等症状
    0.07
    craft
    0.07
    乘坐
    0.07
    是一座
    0.07
    .select
    0.07
    บา
    0.07
    #pragma
    0.06
    .Enabled
    0.06
    /status
    0.06
    Act Density 0.004%

    No Known Activations