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

    Neuronpedia

    INDEX
    Explanations

    social

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nucleotide
    -0.10
     Stainless
    -0.09
     страны
    -0.08
     travelling
    -0.08
     clocks
    -0.08
     navy
    -0.08
     elektrische
    -0.08
     преимущества
    -0.08
     accelerating
    -0.08
    GHz
    -0.08
    POSITIVE LOGITS
    _services
    0.10
     homelessness
    0.09
     �
    0.09
     homeless
    0.09
     compassion
    0.09
    举报
    0.09
     referrals
    0.09
     welfare
    0.09
     refugees
    0.09
     psychopath
    0.09
    Act Density 0.038%

    No Known Activations