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

    Neuronpedia

    INDEX
    Explanations

    condition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kanun
    -0.07
    واج
    -0.07
    등록
    -0.07
    ohana
    -0.07
    _capture
    -0.07
    _fin
    -0.07
     tablets
    -0.07
     planted
    -0.07
    技术
    -0.07
     POR
    -0.07
    POSITIVE LOGITS
    structure
    0.06
    εύ
    0.06
    states
    0.06
    缩
    0.05
    ілі
    0.05
     WW
    0.05
    ){}↵
    0.05
    conomics
    0.05
    зі
    0.05
    ыџN
    0.05
    Act Density 0.004%

    No Known Activations