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

    Neuronpedia

    INDEX
    Explanations

    examples, geographical locations, nationalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Metadata
    0.33
     Liye
    0.33
     않고
    0.32
     Tvam
    0.32
    嘢
    0.31
    📋
    0.31
     prejudice
    0.31
     diathermy
    0.31
     Reuse
    0.31
     OnTrigger
    0.31
    POSITIVE LOGITS
     Japan
    0.49
     например
    0.47
    например
    0.47
    examples
    0.45
     Fiji
    0.45
     Barcelona
    0.44
    例えば
    0.44
     British
    0.43
     ejemplo
    0.43
     Japanese
    0.42
    Act Density 0.255%

    No Known Activations