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

    Neuronpedia

    INDEX
    Explanations

    Code/programming text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nen
    -0.07
     heb
    -0.07
    eba
    -0.07
    Rad
    -0.06
     Directorate
    -0.06
    :d
    -0.06
    руш
    -0.06
    niční
    -0.06
    чески
    -0.06
    č
    -0.06
    POSITIVE LOGITS
     DEBUG
    0.07
    CPU
    0.06
     spyOn
    0.06
     spikes
    0.06
    Credentials
    0.06
    .callbacks
    0.06
    .push
    0.06
     Vietnamese
    0.06
     Things
    0.06
     Revolutionary
    0.06
    Act Density 0.000%

    No Known Activations