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

    Neuronpedia

    INDEX
    Explanations

    files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    right
    -0.08
    Fact
    -0.07
    Cause
    -0.06
    �
    -0.06
     HDF
    -0.06
     conditioned
    -0.06
    cmd
    -0.06
    -F
    -0.06
    ла
    -0.06
    iday
    -0.06
    POSITIVE LOGITS
     фундамент
    0.07
    .Fragment
    0.07
    供应
    0.07
     않은
    0.06
    Ang
    0.06
    보증금
    0.06
     $('
    0.06
     happier
    0.06
     luckily
    0.06
     внутри
    0.06
    Act Density 0.030%

    No Known Activations