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

    Neuronpedia

    INDEX
    Explanations

    photo captions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ERGE
    -0.07
     сент
    -0.06
    АН
    -0.06
     Er
    -0.06
    昌
    -0.06
     Refugee
    -0.06
    leys
    -0.06
    рид
    -0.06
     рос
    -0.06
    仁
    -0.06
    POSITIVE LOGITS
    ummies
    0.06
     Alive
    0.06
    _partner
    0.06
     expected
    0.06
    hic
    0.06
     Econom
    0.06
     investigate
    0.06
     adversity
    0.06
     condo
    0.06
    laví
    0.06
    Act Density 0.011%

    No Known Activations