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

    Neuronpedia

    INDEX
    Explanations

    Technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    THE
    -0.07
    .xlabel
    -0.07
    โซ
    -0.07
    .unpack
    -0.06
    cis
    -0.06
    MESSAGE
    -0.06
    .bio
    -0.06
    ूब
    -0.06
     plot
    -0.06
    /language
    -0.06
    POSITIVE LOGITS
     disability
    0.06
    registered
    0.06
     alright
    0.06
    economic
    0.06
    �
    0.06
    OrNil
    0.06
    erli
    0.06
    utorials
    0.06
     lesser
    0.06
    accine
    0.06
    Act Density 0.148%

    No Known Activations