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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Qed
    -0.07
     Hiring
    -0.07
    ())),
    -0.06
    Dependencies
    -0.06
    declare
    -0.06
    Run
    -0.06
    чі
    -0.06
     kolo
    -0.06
    CLUD
    -0.06
    .role
    -0.06
    POSITIVE LOGITS
     Binder
    0.07
     控
    0.07
     Elli
    0.06
     classification
    0.06
    824
    0.06
     heterosexual
    0.06
     Dustin
    0.06
    �
    0.06
    TCP
    0.06
     Nikol
    0.06
    Act Density 0.001%

    No Known Activations