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

    Neuronpedia

    INDEX
    Explanations

    beings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    麻
    -0.07
     cupid
    -0.07
     nová
    -0.07
     Oscars
    -0.07
     Indo
    -0.06
     nationalists
    -0.06
    �
    -0.06
     formulaire
    -0.06
    urtle
    -0.06
     outskirts
    -0.06
    POSITIVE LOGITS
     beings
    0.25
     decoding
    0.07
     selectable
    0.07
     đề
    0.07
    snapshot
    0.06
    isdigit
    0.06
    -binary
    0.06
    стин
    0.06
     Reggie
    0.06
     히
    0.06
    Act Density 0.002%

    No Known Activations