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

    Neuronpedia

    INDEX
    Explanations

    articles/auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cam
    -0.07
     NETWORK
    -0.07
    Hist
    -0.07
     guilt
    -0.06
    _QU
    -0.06
    OUTH
    -0.06
     Provider
    -0.06
     PERSON
    -0.06
    borne
    -0.06
    amin
    -0.06
    POSITIVE LOGITS
     ─
    0.07
    509
    0.06
    -chevron
    0.06
     invers
    0.06
    =options
    0.06
    .retry
    0.06
     hit
    0.06
     Cliente
    0.06
    othermal
    0.05
     clin
    0.05
    Act Density 0.012%

    No Known Activations