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

    Neuronpedia

    INDEX
    Explanations

    credit monitoring and errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    osc
    -0.07
    und
    -0.07
    ुँ
    -0.07
    decay
    -0.07
    imp
    -0.07
    وا
    -0.06
    anks
    -0.06
     Columbia
    -0.06
    $b
    -0.06
     Locate
    -0.06
    POSITIVE LOGITS
     coach
    0.07
    學
    0.06
    .FromResult
    0.06
    .isLoading
    0.06
     MainForm
    0.06
     науков
    0.06
    �
    0.06
    Shared
    0.06
    UnderTest
    0.06
    [train
    0.06
    Act Density 0.051%

    No Known Activations