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

    Neuronpedia

    INDEX
    Explanations

    communication and understanding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scheduling
    -0.09
    Scheduling
    -0.08
     tricks
    -0.08
     nozzle
    -0.07
     Dop
    -0.07
     embol
    -0.07
     unfortunate
    -0.07
     Scheduling
    -0.07
     사업
    -0.07
     displacement
    -0.07
    POSITIVE LOGITS
     skeptic
    0.12
     epistem
    0.11
    观点
    0.11
     beliefs
    0.11
     heterosexual
    0.10
     worldview
    0.10
    belief
    0.10
    知乎
    0.09
     ideological
    0.09
     concili
    0.09
    Act Density 0.106%

    No Known Activations