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

    Neuronpedia

    INDEX
    Explanations

    Court

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cal
    -0.06
    네
    -0.06
    _vote
    -0.06
    jenis
    -0.06
    .av
    -0.06
    िसस
    -0.06
    왕
    -0.06
    ..'
    -0.06
    "?↵↵
    -0.06
     tender
    -0.06
    POSITIVE LOGITS
     Pry
    0.08
    kla
    0.07
    Chris
    0.07
     LastName
    0.06
     Indices
    0.06
     �
    0.06
     Kro
    0.06
     Shopping
    0.06
     dental
    0.06
     preamble
    0.06
    Act Density 0.005%

    No Known Activations