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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orning
    -0.07
    home
    -0.07
     residual
    -0.07
     home
    -0.07
    ocked
    -0.07
     vintage
    -0.07
     tether
    -0.06
     arrive
    -0.06
    state
    -0.06
     displaced
    -0.06
    POSITIVE LOGITS
    .modelo
    0.06
    PTS
    0.06
     όμως
    0.06
     governments
    0.06
    .Files
    0.06
     знать
    0.06
     ancest
    0.06
     Tradable
    0.06
    ulumi
    0.06
    MFLOAT
    0.06
    Act Density 0.128%

    No Known Activations