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

    Neuronpedia

    INDEX
    Explanations

    War

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aż
    -0.07
    ocus
    -0.07
     아이
    -0.07
    lication
    -0.07
     advocacy
    -0.06
    igration
    -0.06
     değ
    -0.06
    jącego
    -0.06
    ходим
    -0.06
     decoder
    -0.06
    POSITIVE LOGITS
    _MSK
    0.08
     Zar
    0.08
    <r
    0.07
    !,↵
    0.07
    ;br
    0.07
    _sk
    0.07
    ܜ
    0.07
     Barcelona
    0.07
     mỡ
    0.07
     Berkeley
    0.07
    Act Density 0.041%

    No Known Activations