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

    Neuronpedia

    INDEX
    Explanations

    ordering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     régl
    -0.07
     Extension
    -0.07
     desc
    -0.07
     slider
    -0.07
     skipped
    -0.06
     scatter
    -0.06
    ➾
    -0.06
    闲置
    -0.06
     如
    -0.06
    Candidates
    -0.06
    POSITIVE LOGITS
     healer
    0.07
    efs
    0.07
    ساء
    0.07
    _Parms
    0.07
     find
    0.07
     노력
    0.07
    ULLET
    0.07
    غار
    0.06
    ]initWith
    0.06
     girlfriends
    0.06
    Act Density 0.061%

    No Known Activations