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

    Neuronpedia

    INDEX
    Explanations

    conflict/unrest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Capabilities
    -0.07
     çalışmaları
    -0.06
    *time
    -0.06
    recv
    -0.06
    _macros
    -0.06
     lẫn
    -0.06
     “…
    -0.06
     Regulatory
    -0.06
    Assistant
    -0.06
    ccd
    -0.06
    POSITIVE LOGITS
    È
    0.07
    ik
    0.06
     Nom
    0.06
    STORE
    0.06
    hotel
    0.06
     ней
    0.06
     {}
↵
    0.06
    _orig
    0.06
     départ
    0.06
    STRU
    0.06
    Act Density 0.000%

    No Known Activations