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

    Neuronpedia

    INDEX
    Explanations

    phrase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     finns
    -0.07
    랜드
    -0.07
     matters
    -0.06
     ancor
    -0.06
     estado
    -0.06
    ULLET
    -0.06
     roadmap
    -0.06
     oggi
    -0.06
    투
    -0.06
    ู
    -0.06
    POSITIVE LOGITS
     Kate
    0.07
     mike
    0.07
     }*/↵
    0.06
     Philip
    0.06
    									↵
    0.06
    .eth
    0.06
     Dough
    0.06
    ##↵↵
    0.06
     dlouho
    0.06
     Philadelphia
    0.06
    Act Density 0.005%

    No Known Activations