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

    Neuronpedia

    INDEX
    Explanations

    hom

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kale
    -0.08
     Ca
    -0.07
    ail
    -0.07
    Should
    -0.07
    ergus
    -0.07
    ে
    -0.07
     электр
    -0.07
     frail
    -0.07
    ssa
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     hom
    0.17
     Hom
    0.14
    Hom
    0.13
     homogeneous
    0.11
    hom
    0.11
     đồng
    0.09
     homosexuality
    0.08
     anonym
    0.08
     homosexual
    0.08
     hrom
    0.08
    Act Density 0.010%

    No Known Activations